BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163813Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209@linklings.com
SUMMARY:Technical Papers Fast-Forward
DESCRIPTION:A 160 minutes preview session of all Technical Papers will als
 o be held on the first day of the event where author(s) of each paper get 
 less than a minute to wow the attendees with a brief overview of their wor
 k.\n\nC-shells: Deployable Gridshells with Curved Beams\n\nWe introduce a 
 computational pipeline for simulating and designing C-shells, a new class 
 of planar-to-spatial deployable linkage structures. A C-shell is composed 
 of curved flexible beams connected at rotational joints that can be assemb
 led in a stress-free planar configuration. When actuated, the e...\n\n\nQu
 entin Becker, Seiichi Suzuki, and Yingying Ren (EPFL); Davide Pellis (ISTI
  - CNR); Julian Panetta (University of California Davis); and Mark Pauly (
 EPFL)\n---------------------\nNeural Gradient Learning and Optimization fo
 r Oriented Point Normal Estimation\n\nWe propose Neural Gradient Learning 
 (NGL), a deep learning approach to learn gradient vectors with consistent 
 orientation from 3D point clouds for normal estimation. It has excellent g
 radient approximation properties for the underlying geometry of the data. 
 We utilize a simple neural network to para...\n\n\nQing Li (Tsinghua Unive
 rsity), Huifang Feng (Xiamen University), Kanle Shi (Kuaishou Technology),
  Yi Fang (New York University), Yu-Shen Liu (Tsinghua University), and Zhi
 zhong Han (Wayne State University)\n---------------------\nShadow Harmoniz
 ation for Realistic Compositing\n\nCompositing virtual objects into real b
 ackground images requires one to carefully match the scene's camera parame
 ters, surface geometry, textures, and lighting to obtain plausible renderi
 ngs.\nRecent learning approaches have shown many scene properties can be e
 stimated from images, resulting in robus...\n\n\nLucas Valença and Jinsong
  Zhang (Université Laval), Michaël Gharbi and Yannick Hold-Geoffroy (Adobe
 ), and Jean-François Lalonde (Université Laval)\n---------------------\nTo
 RoS: A Topology Optimization Approach for Designing Robotic Skins\n\nSoft 
 robotics offers unique advantages in manipulating fragile or deformable\no
 bjects, human-robot interaction, and exploring inaccessible terrain. How-\
 never, designing soft robots that produce large, targeted deformations is\
 nchallenging. In this paper, we propose a new methodology for designing\ns
 oft...\n\n\nJuan Sebastian Montes Maestre, Ronan Hinchet, Stelian Coros, a
 nd Bernhard Thomaszewski (ETH Zürich)\n---------------------\nC·ASE: Learn
 ing Conditional Adversarial Skill Embeddings for Physics-based Characters\
 n\nWe present C·ASE, an efficient and effective framework that learns cond
 itional Adversarial Skill Embeddings for physics-based characters. Our phy
 sically simulated character can learn a diverse repertoire of skills while
  providing controllability in the form of direct manipulation of the skill
 s to be...\n\n\nZhiyang Dou (The University of Hong Kong (HKU)), Xuelin Ch
 en and Qingnan Fan (Tencent AI Lab), Taku Komura (University of Hong Kong)
 , and Wenping Wang (Texas A&M University)\n---------------------\nACE: Adv
 ersarial Correspondence Embedding for Cross Morphology Motion Retargeting 
 from Human to Nonhuman Characters\n\nMotion retargeting is a promising app
 roach for generating natural and compelling motions for nonhuman character
 s. However, it is challenging to translate human movements into semantical
 ly equivalent motions for target characters with very different morphologi
 es due to ambiguity. This work presents a...\n\n\nTianyu Li (Georgia Insti
 tute of Technology), Jungdam Won (Seoul National University), Alexander Cl
 egg (Meta), Jeonghwan Kim (Georgia Institute of Technology), Akshara Rai (
 Meta), and Sehoon Ha (Georgia Institute of Technology)\n------------------
 ---\nHand Pose Estimation with Mems-Ultrasonic Sensors\n\nHand tracking is
  an important aspect of human-computer interaction and has a wide range of
  applications in extended reality devices. However, current hand motion ca
 pture methods suffer from various limitations. For instance, visual-based 
 hand pose estimation is susceptible to self-occlusion and chan...\n\n\nQia
 ng Zhang, Yuanqiao Lin, Yubin Lin, and Szymon Rusinkiewicz (Princeton Univ
 ersity)\n---------------------\nDR-Occluder: Generating Occluders using Di
 fferentiable Rendering\n\nThe target of the occluder is to use very few fa
 ces to maintain similar occlusion properties of the original 3D model.\nIn
  this paper, we present DR-Occluder, a novel coarse-to-fine framework for 
 occluder generation that leverages differentiable rendering to optimize a 
 triangle set to an occluder. Un...\n\n\nJiaxian Wu, Yue Lin, and Dehui Lu 
 (NetEase Games AI Lab)\n---------------------\nA Micrograin BSDF Model for
  the Rendering of Porous Layers\n\nWe introduce a new BSDF model for the r
 endering of porous layers, as found on surfaces covered by dust, rust, dir
 t, or sprayed paint. \nOur approach is based on a distribution of elliptic
 al opaque micrograins, extending the Trowbridge-Reitz (GGX) distribution [
 Trowbridge1975,Walter2007] to handle por...\n\n\nSimon Lucas (Université d
 e Bordeaux, INRIA); Mickael Ribardiere (Université de Poitiers); and Romai
 n Pacanowski and Pascal Barla (INRIA)\n---------------------\nVariational 
 Barycentric Coordinates\n\nWe propose a variational technique to optimize 
 for generalized barycentric coordinates that offers additional artistic co
 ntrol compared to existing models. Prior work represents barycentric coord
 inates using meshes or closed-form formulae, in practice limiting the choi
 ce of objective function. In co...\n\n\nAna Dodik (MIT CSAIL); Oded Stein 
 (University of Southern California, MIT CSAIL); and Vincent SItzmann and J
 ustin Solomon (MIT CSAIL)\n---------------------\nNeural Categorical Prior
 s for Physics-Based Character Control\n\nRecent advances in learning reusa
 ble motion priors have demonstrated their effectiveness in generating natu
 ralistic behaviors. In this paper, we propose a new learning framework in 
 this paradigm for controlling physics-based characters with significantly 
 improved motion quality and diversity over ex...\n\n\nQingxu Zhu, He Zhang
 , Mengting Lan, and Lei Han (Tencent)\n---------------------\nK-surfaces: 
 Bézier-Splines Interpolating at Gaussian Curvature Extrema\n\nK-surfaces a
 re an interactive modeling technique for Bézier-spline surfaces. Inspired 
 by 𝜅-curves by [Yan et al. 2017], each patch provides a single control poi
 nt that is being interpolated at a local extremum of Gaussian curvature.\n
 The challenge is to solve the inverse problem of finding th...\n\n\nTobias
  Djuren, Maximilian Kohlbrenner, and Marc Alexa (Technische Universität Be
 rlin)\n---------------------\nThin On-Sensor Nanophotonic Array Cameras\n\
 nToday's commodity camera systems rely on compound optical systems to map 
 light originating from the scene to positions on the sensor where it gets 
 recorded as an image. To achieve an accurate mapping without optical aberr
 ations, i.e., deviations from Gauss' linear optics model, typical lens sys
 tems ...\n\n\nPraneeth Chakravarthula (Princeton University); Jipeng Sun (
 Princeton University, Northwestern University); Xiao Li, Chenyang Lei, Gen
 e Chou, and Mario Bijelic (Princeton University); Johannes Froesch and Ark
 a Majumdar (University of Washington); and Felix Heide (Princeton Universi
 ty)\n---------------------\nRectifying Strip Patterns\n\nA straight flat s
 trip of inextensible material can be bent into curved strips aligned with 
 arbitrary space curves. The large shape variety of these so-called rectify
 ing strips makes them candidates for shape modeling, especially in applica
 tions such as architecture where simple elements are preferre...\n\n\nBolu
 n Wang and Hui Wang (King Abdullah University of Science and Technology (K
 AUST)), Eike Schling (The University of Hong Kong), and Helmut Pottmann (K
 ing Abdullah University of Science and Technology (KAUST))\n--------------
 -------\nFusing Monocular Images and Sparse IMU Signals for Real-time Huma
 n Motion Capture\n\nEither RGB images or inertial signals have been used f
 or the task of motion capture (mocap), but combining them together is a ne
 w and interesting topic. We believe that the combination is complementary 
 and able to solve the inherent difficulties of using one modality input, i
 ncluding occlusions, ext...\n\n\nShaohua Pan, Qi Ma, and Xinyu Yi (Tsinghu
 a University); Weifeng Hu, Xiong Wang, Xingkang ZHOU, and Jijunnan LI (OPP
 O Research Institute); and Feng Xu (Tsinghua University)\n----------------
 -----\nEfficient Cone Singularity Construction for Conformal Parameterizat
 ions\n\nWe propose an efficient method to construct sparse cone singularit
 ies under distortion-bounded constraints for conformal parameterizations. 
 Central to our algorithm is using the technique of shape derivatives to mo
 ve cones for distortion reduction without changing the number of cones. In
  particular,...\n\n\nMo Li, Qing Fang, Zheng Zhang, Ligang Liu, and Xiao-M
 ing Fu (University of Science and Technology of China)\n------------------
 ---\nVASCO: Volume and Surface Co-Decomposition for Hybrid Manufacturing\n
 \nAdditive and subtractive hybrid manufacturing (ASHM) involves the altern
 ating use of additive and subtractive manufacturing techniques, which prov
 ides unique advantages for fabricating complex geometries with otherwise i
 naccessible surfaces. However, a significant challenge lies in ensuring to
 ol acc...\n\n\nFanchao Zhong, Haisen Zhao, Haochen Li, Xin Yan, and Jikai 
 Liu (Shandong University); Baoquan Chen (Peking University); and Lin Lu (S
 handong University)\n---------------------\nReal-time Height-field Simulat
 ion of Sand and Water Mixtures\n\nWe propose a height-field-based real-tim
 e simulation method for sand and water mixtures. Inspired by the shallow-w
 ater assumption, our approach extends the governing equations to handle tw
 o-phase flows of sand and water using height fields. Our depth-integrated 
 governing equations can model the elas...\n\n\nHaozhe Su (Rutgers Universi
 ty, LightSpeed Studios); Siyu Zhang and Zherong Pan (LightSpeed Studios); 
 Mridul Aanjaneya (Rutgers University); and Xifeng Gao and Kui Wu (LightSpe
 ed Studios)\n---------------------\nLocally-Adaptive Level-of-Detail for H
 ardware-Accelerated Ray Tracing\n\nWe introduce an adaptive level-of-detai
 l technique for ray tracing triangle meshes that aims to reduce the memory
  bandwidth used during ray traversal, which can be the bottleneck for rend
 ering time with large scenes and the primary consumer of energy. We propos
 e a specific data structure for hierarc...\n\n\nJacob Haydel (University o
 f Utah); Cem Yuksel (University of Utah, Roblox); and Larry Seiler (Indepe
 ndent)\n---------------------\nMuscleVAE: Model-Based Controllers of Muscl
 e-Actuated Characters\n\nIn this paper, we present a simulation and contro
 l framework for generating biomechanically plausible motion for muscle-act
 uated characters. We incorporate a fatigue dynamics model, the 3CC-r model
 , into the widely-adopted Hill-type muscle model to simulate the developme
 nt and recovery of fatigue in...\n\n\nYusen Feng, Xiyan Xu, and Libin Liu 
 (Peking University)\n---------------------\nMulti-color Holograms Improve 
 Brightness in Holographic Displays\n\nHolographic displays generate Three-
 Dimensional (3D) images by displaying single-color holograms time-sequenti
 ally, each lit by a single-color light source. However, representing each 
 color one by one limits brightness in holographic displays.\n\nThis paper 
 introduces a new driving scheme for realizin...\n\n\nKoray Kavaklı (Koç Un
 iversity), Liang Shi (Massachusetts Institute of Technology), Hakan Urey (
 Koç University), Wojciech Matusik (Massachusetts Institute of Technology),
  and Kaan Akşit (University College London (UCL))\n---------------------\n
 The effect of display capabilities on the gloss consistency between real a
 nd virtual objects\n\nA faithful reproduction of gloss is inherently diffi
 cult because of the limited dynamic range, peak luminance, and 3D capabili
 ties of display devices. This work investigates how the display capabiliti
 es affect gloss appearance with respect to a real-world reference object. 
 To this end, we employ an ...\n\n\nBin Chen (Max-Planck-Institut für Infor
 matik); Akshay Jindal (Intel Corporation, University of Cambridge); Michal
  Piovarči (Institute of Science and Technology Austria); Chao Wang and Han
 s-Peter Seidel (Max-Planck-Institut für Informatik); Piotr Didyk (Universi
 tà della Svizzera italiana); Karol Myszkowski (Max-Planck-Institut für Inf
 ormatik); Ana Serrano (Universidad de Zaragoza); and Rafał K. Mantiuk (Uni
 versity of Cambridge)\n---------------------\nSFLSH: Shape-Dependent Soft-
 Flesh Avatars\n\nWe present a multi-person soft-tissue avatar model. This 
 model maps a body shape descriptor to heterogeneous geometric and mechanic
 al parameters of a soft-tissue model across the body, effectively producin
 g a shape-dependent parametric soft avatar model. The design of the model 
 overcomes two major c...\n\n\nPablo Ramón, Cristian Romero, Javier Tapia, 
 and Miguel A. Otaduy (Universidad Rey Juan Carlos)\n---------------------\
 nFluid Simulation on Neural Flow Maps\n\nWe introduce Neural Flow Maps, a 
 novel simulation method bridging the emerging paradigm of implicit neural 
 representations with fluid simulation based on the theory of flow maps, to
  achieve state-of-the-art simulation of inviscid fluid phenomena. We devis
 e a novel hybrid neural field representation,...\n\n\nYitong Deng (Dartmou
 th College), Hong-Xing Yu (Stanford University), Diyang Zhang (Dartmouth C
 ollege), Jiajun Wu (Stanford University), and Bo Zhu (Dartmouth College)\n
 ---------------------\n360° Reconstruction From a Single Image Using Space
  Carved Outpainting\n\nWe introduce POP3D, a novel framework that creates 
 a full $360^\circ$-view 3D model from a single image. POP3D resolves two p
 rominent issues that limit the single-view reconstruction. Firstly, POP3D 
 offers substantial generalizability to arbitrary categories, a trait that 
 previous methods struggle t...\n\n\nNuri Ryu, Minsu Gong, and Geonung Kim 
 (POSTECH); Joo-Haeng Lee (Pebblous Inc.); and Sunghyun Cho (POSTECH, Pebbl
 ous Inc.)\n---------------------\nAn Unified $\lambda$-subdivision Scheme 
 for Quadrilateral Meshes with Optimal Curvature Performance in Extraordina
 ry Regions\n\nWe propose an unified $\lambda$-subdivision scheme with a co
 ntinuous family of tuned subdivisions for quadrilateral meshes. Main subdi
 vision stencil parameters of the unified scheme are represented as spline 
 functions of the subdominant eigenvalue $\lambda$ of respective subdivisio
 n matrices and the...\n\n\nWeiyin Ma, Xu Wang, and Yue Ma (City University
  of Hong Kong)\n---------------------\nKirchhoff-Love Shells with Arbitrar
 y Hyperelastic Materials\n\nKirchhoff-Love shells are commonly used in man
 y branches of engineering, including in computer graphics, but have so far
  been simulated only under limited nonlinear material options. We derive t
 he Kirchhoff-Love thin-shell mechanical energy for an arbitrary 3D volumet
 ric hyperelastic material, inclu...\n\n\nJiahao Wen and Jernej Barbic (Uni
 versity of Southern California)\n---------------------\nTowards Garment Se
 wing Pattern Reconstruction from a Single Image\n\nGarment sewing pattern 
 represents the intrinsic rest shape of a garment, and is the core for many
  applications like fashion design, virtual try-on, and digital avatars. In
  this work, we explore the challenging problem of recovering garment sewin
 g patterns from daily photos for augmenting these appli...\n\n\nLijuan Liu
  (Sea AI Lab); Xiangyu Xu (Xi'an Jiaotong University, Sea AI Lab); and Zhi
 jie Lin, Jiabin Liang, and Shuicheng Yan (Sea AI Lab)\n-------------------
 --\nShrink & Morph: 3D-printed self-shaping shells actuated by a shape mem
 ory effect\n\nWhile 3D printing enables the customization and home fabrica
 tion of a wide range of shapes, fabricating freeform thin-shells remains c
 hallenging. As layers misalign with the curvature, they incur structural d
 eficiencies, while the curved shells require large support structures, typ
 ically using more ...\n\n\nDavid Jourdan (INRIA Nancy - Grand Est, LORIA);
  Camille Schreck (Inria); and Pierre-Alexandre Hugron, Jonas Martinez, and
  Sylvain Lefebvre (INRIA)\n---------------------\nGeoLatent: A Geometric A
 pproach to Latent Space Design for Deformable Shape Generators\n\nWe study
  how to optimize the latent space of neural shape generators that map late
 nt codes to 3D deformable shapes. The key focus is to look at a deformable
  shape generator from a differential geometry perspective. We define a Rie
 mannian metric based on as-rigid-as-possible and as-conformal-as-possi...\
 n\n\nHaitao Yang, Bo Sun, Liyan Chen, Amy Pavel, and Qixing Huang (Univers
 ity of Texas at Austin)\n---------------------\nShaDDR: Interactive Exampl
 e-Based Geometry and Texture Generation via 3D Shape Detailization and Dif
 ferentiable Rendering\n\nWe present ShaDDR, an example-based deep generati
 ve neural network which produces a high-resolution textured 3D shape throu
 gh geometry detailization and conditional texture generation applied to an
  input coarse voxel shape. Trained on a small set of detailed and textured
  exemplar shapes, our method ...\n\n\nQimin Chen, Zhiqin Chen, Hang Zhou, 
 and Hao Zhang (Simon Fraser University)\n---------------------\nExample-Ba
 sed Sampling with Diffusion Models\n\nMuch effort has been put into develo
 ping samplers with specific properties, such as producing blue noise, low-
 discrepancy, lattice or Poisson disk samples. These samplers can be slow i
 f they rely on optimization processes, may rely on a wide range of numeric
 al methods, are not always differentiable....\n\n\nBastien Doignies (Unive
 rsité Claude Bernard Lyon, CNRS); Nicolas Bonneel, David Coeurjolly, and J
 ulie Digne (CNRS, LIRIS); Loïs Paulin (Université Claude Bernard Lyon / CN
 RS, Adobe); and Jean-Claude Iehl and Victor Ostromoukhov (Université Claud
 e Bernard Lyon, CNRS)\n---------------------\nEfficient Hybrid Zoom using 
 Camera Fusion on Mobile Phones\n\nDSLR cameras can achieve multiple zoom l
 evels via shifting lens distances or swapping lens types. However, these t
 echniques are not possible on smartphone devices due to space constraints.
  Most smartphone manufacturers adopt a hybrid zoom system: commonly a Wide
  (W) camera at a low zoom level and a ...\n\n\nXiaotong Wu, Wei-Sheng Lai,
  and Yichang Shih (Google Inc.); Charles Herrmann and Michael Krainin (Goo
 gle Research); Deqing Sun (Google); and Chia-Kai Liang (Google Inc.)\n----
 -----------------\nWhat is the Best Automated Metric for Text to Motion Ge
 neration?\n\nThere is growing interest in generating skeleton-based human 
 motions from natural language descriptions. While most efforts have focuse
 d on developing better neural architectures for this task, there has been 
 no significant work on determining the proper evaluation metric. Human eva
 luation is the ul...\n\n\nJordan Voas, Yili Wang, Qixing Huang, and Raymon
 d Mooney (University of Texas at Austin)\n---------------------\nDomain-Ag
 nostic Tuning-Encoder for Fast Personalization of Text-To-Image Models\n\n
 Text-to-image (T2I) personalization allows users to guide the creative ima
 ge generation process by combining their own visual concepts in natural la
 nguage prompts. \nRecently, encoder-based techniques have emerged as a new
  effective approach for T2I personalization, reducing the need for multipl
 e ima...\n\n\nMoab Arar (Tel-Aviv University); Rinon Gal (Tel Aviv Univers
 ity, NVIDIA Research); Yuval Atzmon (NVIDIA Research); Gal Chechik (NVIDIA
  Research, Bar-Ilan University); Daniel Cohen-Or (Tel Aviv University); Ar
 iel Shamir (Reichman University (IDC)); and Amit H. Bermano (Tel Aviv Univ
 ersity)\n---------------------\nFrom Skin to Skeleton : Towards Biomechani
 cally Accurate 3D Digital Humans\n\nGreat progress has been made in estima
 ting 3D human pose and shape from images and video by training neural netw
 orks to directly regress the parameters of parametric human models like SM
 PL.\nHowever, existing body models have simplified kinematic structures th
 at do not correspond to accurate joint lo...\n\n\nMarilyn Keller (Max Plan
 ck Institute for Intelligent Systems), Keenon Werling (Stanford University
 ), Soyong Shin (Max-Planck-Institut für Informatik), Scott Delp (Stanford)
 , Sergi Pujades (INRIA), Karen Liu (Stanford University), and Michael Blac
 k (Max Planck Institute for Intelligent Systems)\n---------------------\nC
 ontent-based Search for Deep Generative Models\n\nThe growing proliferatio
 n of customized and pretrained generative models has made it infeasible fo
 r a user to be fully cognizant of every model in existence. To address thi
 s need, we introduce the task of content-based model search: given a query
  and a large set of generative models, finding the mod...\n\n\nDaohan Lu, 
 Sheng-Yu Wang, Nupur Kumari, Rohan Agarwal, and Mia Tang (Carnegie Mellon 
 University); David Bau (Northeastern University); and Jun-Yan Zhu (Carnegi
 e Mellon University)\n---------------------\nA Hessian-Based Field Deforme
 r for Real-Time Topology-Aware Shape Editing\n\nShape manipulation is a ce
 ntral research topic in computer graphics. Topology editing, such as break
 ing apart connections, joining disconnected ends, and filling/opening a to
 pological hole, is generally more challenging than geometry editing. In th
 is paper, we observe that the saddle points of the s...\n\n\nYunxiao Zhang
 , Zixiong Wang, Zihan Zhao, and Rui Xu (Shandong University); Shuangmin Ch
 en (Qingdao University of Science and Technology); Shiqing Xin (Shandong U
 niversity); Wenping Wang (Texas A&M University); and Changhe Tu (Shandong 
 University)\n---------------------\nActRay: Online Active Ray Sampling for
  Radiance Fields\n\nThanks to the high-quality reconstruction and photorea
 listic rendering, the Neural Radiance Field (NeRF) has garnered extensive 
 attention and has been continuously improved. Despite its high visual qual
 ity, the prohibitive training time limits its practical application. Altho
 ugh significant accelera...\n\n\nJiangkai Wu, Liming Liu, Yunpeng Tan, Qua
 nlu Jia, Haodan Zhang, and Xinggong Zhang (Peking University)\n-----------
 ----------\nCommonsense Knowledge-Driven Joint Reasoning Approach for Obje
 ct Retrieval in Virtual Reality\n\nOut-of-reach object retrieval is an imp
 ortant task in virtual reality (VR). Gesture-based approach, one of the mo
 st commonly used approaches, enables bare-hand, eyes-free, and direct retr
 ieval by using assigned gestures. However, it is difficult to retrieve an 
 object from plenty of objects accuratel...\n\n\nHaiyan Jiang (Beijing Inst
 itute of Technology; National Key Laboratory of General Artificial Intelli
 gence, Beijing Institute for General Artificial Intelligence (BIGAI)); Don
 dong Weng (Beijing Institute of Technology); Xiaonuo Dongye (Beijing Insti
 tute of Technology; National Key Laboratory of General Artificial Intellig
 ence, Beijing Institute for General Artificial Intelligence (BIGAI)); Le L
 uo (Beijing Institute of Technology); and Zhenliang Zhang (National Key La
 boratory of General Artificial Intelligence, Beijing Institute for General
  Artificial Intelligence (BIGAI))\n---------------------\nMetaLayer: A Met
 a-learned BSDF Model for Layered Materials\n\nReproducing the appearance o
 f arbitrary layered materials has long been a critical challenge in comput
 er graphics, with regard to the demanding requirements of both physical ac
 curacy and low computation cost. Recent studies have demonstrated promisin
 g results by learning-based representations that i...\n\n\nJie Guo, Zeru L
 i, and Xueyan He (Nanjing University); Beibei Wang (Nankai University, Nan
 jing University of Science and Technology); Wenbin Li and Yanwen Guo (Nanj
 ing University); and Ling-Qi Yan (University of California, Santa Barbara)
 \n---------------------\nHigh-Fidelity and Real-Time Novel View Synthesis 
 for Dynamic Scenes\n\nThis paper aims to tackle the challenge of dynamic v
 iew synthesis from multi-view videos. The key observation is that while pr
 evious grid-based methods offer consistent rendering, they fall short in c
 apturing appearance details on a complex dynamic scene, a domain where mul
 ti-view image-based method...\n\n\nHaotong Lin (State Key Laboratory of CA
 D & CG, Zhejiang University); Sida Peng (Zhejiang University); and Zhen Xu
 , Tao Xie, Xingyi He, Hujun Bao, and Xiaowei Zhou (State Key Laboratory of
  CAD & CG, Zhejiang University)\n---------------------\nEfficient Graphics
  Representation with Differentiable Indirection\n\nWe introduce differenti
 able indirection -- a novel learned primitive that employs differentiable 
 multi-scale lookup tables as an effective substitute for traditional compu
 te and data operations across the graphics pipeline. We demonstrate its fl
 exibility on a number of graphics tasks, i.e., geometri...\n\n\nSayantan D
 atta (McGill University, Meta Reality Labs); Carl Marshall (Meta); Derek N
 owrouzezahrai (McGill University, Meta); and Zhao Dong and Zhengqin Li (Me
 ta)\n---------------------\nScene-aware Activity Program Generation with L
 anguage Guidance\n\nWe address the problem of scene-aware activity program
  generation, which requires decomposing a given activity task into instruc
 tions that can be sequentially performed within a target scene to complete
  the activity. While existing methods have shown the ability to generate r
 ational or executable pr...\n\n\nZejia Su (Shenzhen University), Qingnan F
 an (Vivo), Xuelin Chen (Tencent AI Lab), Oliver van Kaick (Carleton Univer
 sity), and Hui Huang and Ruizhen Hu (Shenzhen University)\n---------------
 ------\nLearning based 2D Irregular Shape Packing\n\n2D irregular shape pa
 cking is a necessary step to arrange UV patches of a 3D model within a tex
 ture atlas for memory-efficient appearance rendering in computer graphics.
  Being a joint, combinatorial decision-making problem involving all patch 
 positions and orientations, this problem has well-known N...\n\n\nZeshi Ya
 ng and Zherong Pan (Tencent America), Manyi Li (Shandong University), and 
 Kui Wu and Xifeng Gao (Tencent America)\n---------------------\nOnline Sce
 ne CAD Recomposition via Autonomous Scanning\n\nAutonomous surface reconst
 ruction of 3D scenes has been intensely studied in recent years, however, 
 it is still difficult to accurately reconstruct all the surface details of
  complex scenes with complicated object relations and severe occlusions, w
 hich makes the reconstruction results not suitable f...\n\n\nChanghao Li a
 nd Junfu Guo (University of Science and Technology of China), Ruizhen Hu (
 Shenzhen University), and Ligang Liu (University of Science and Technology
  of China)\n---------------------\nHigh-Order Moment-Encoded Kinetic Simul
 ation of Turbulent Flows\n\nKinetic solvers for incompressible fluid simul
 ation were designed to run efficiently on massively parallel architectures
  such as GPUs. While these lattice Boltzmann solvers have recently proven 
 much faster and more accurate than common macroscopic Navier-Stokes-based 
 solvers in graphics, it is alway...\n\n\nWei Li, Tongtong Wang, Zherong Pa
 n, Xifeng Gao, and Kui Wu (LightSpeed Studios) and Mathieu Desbrun (Inria/
 X)\n---------------------\nBakedAvatar: Baking Neural Fields for Real-Time
  Head Avatar Synthesis\n\nSynthesizing photorealistic 4D human head avatar
 s from videos is essential for VR/AR, telepresence, and video game applica
 tions. Although existing Neural Radiance Fields (NeRF)-based methods achie
 ve high-fidelity results, the computational expense limits their use in re
 al-time applications. To overc...\n\n\nHao-Bin Duan (Beihang University); 
 Miao Wang (Beihang University, Zhongguancun Laboratory); Jin-Chuan Shi and
  Xu-Chuan Chen (Beihang University); and Yan-Pei Cao (Tencent)\n----------
 -----------\nNeural Stochastic Poisson Surface Reconstruction\n\nReconstru
 cting a surface from a point cloud is an underdetermined problem. We propo
 se using a neural network to study and quantify this reconstruction uncert
 ainty under a Poisson smoothness prior. Our algorithm addresses the main l
 imitations of existing work and can be fully integrated into the 3D s...\n
 \n\nSilvia Sellán (University of Toronto) and Alec Jacobson (University of
  Toronto, Adobe Research)\n---------------------\nEgo3DPose: Capturing 3D 
 Cues from Binocular Egocentric Views\n\nWe present Ego3DPose, a highly acc
 urate binocular egocentric 3D pose reconstruction system. The binocular eg
 ocentric setup offers practicality and usefulness in various applications,
  however, it remains largely under-explored. It has been suffering from lo
 w pose estimation accuracy due to viewing di...\n\n\nTaeho Kang and Kyungj
 in Lee (Seoul National University), Jinrui Zhang (Central South University
 ), and Youngki Lee (Seoul National University)\n---------------------\nHyp
 erDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single
  Image\n\n3D content creation from a single image is a long-standing yet h
 ighly desirable task. Recent advances introduce 2D diffusion priors, yield
 ing reasonable results. However, existing methods are not hyper-realistic 
 enough for post-generation usage, as users cannot view, render and edit th
 e resulting 3D...\n\n\nTong Wu and Zhibing Li (The Chinese University of H
 ong Kong, Shanghai AI Laboratory); Shuai Yang (Shanghai Jiao Tong Universi
 ty, Shanghai AI Laboratory); Pan Zhang (Shanghai AI Laboratory); Xingang P
 an (Max Planck Institute for Informatics); Jiaqi Wang (Shanghai AI Laborat
 ory); Dahua Lin (The Chinese University of Hong Kong, Shanghai AI Laborato
 ry); and Ziwei Liu (Nanyang Technological University)\n-------------------
 --\nDROP: Dynamics Responses from Human Motion Prior and Projective Dynami
 cs\n\nSynthesizing realistic human movements, dynamically responsive to th
 e environment, is a long-standing objective in character animation, with a
 pplications in computer vision, sports, and healthcare, for motion predict
 ion and data augmentation. Recent kinematics-based generative motion model
 s offer im...\n\n\nYifeng Jiang (Stanford University), Jungdam Won (Seoul 
 National University), Yuting Ye (Meta Reality Labs Research), and C. Karen
  Liu (Stanford University)\n---------------------\nAdaptive Recurrent Fram
 e Prediction with Learnable Motion Vectors\n\nThe utilization of dedicated
  ray tracing graphics cards has contributed to the production of stunning 
 visual effects in real-time rendering. However, the demand for high frame 
 rates and high resolutions remains a challenge to be addressed. A crucial 
 technique for increasing frame rate and resolution...\n\n\nZhizhen Wu (Sta
 te Key Lab of CAD&CG, Zhejiang University); Chenyu Zuo (State Key Lab of C
 AD&CG, State Key Laboratory of CAD & CG, Zhejiang University); Yuchi Huo (
 State Key Lab of CAD&CG, Zhejiang University; Zhejiang Lab); Yazhen Yuan (
 Tencent); Yifan Peng (The University of Hong Kong (HKU)); Guiyang Pu (Chin
 a Mobile (Hangzhou) Information Technology Co., Ltd); and Rui Wang and Huj
 un Bao (State Key Lab of CAD&CG, Zhejiang University)\n-------------------
 --\nReparamCAD: Zero-shot CAD Re-Parameterization for Interactive Manipula
 tion\n\nParametric CAD models encode entire families of shapes that should
 , in principle, be easy for designers to explore, but are in practice diff
 icult to manipulate due to implicit semantic constraints between parameter
  values. Finding and enforcing these semantic constraints purely from geom
 etry or prog...\n\n\nMilin Kodnongbua and Benjamin Jones (University of Wa
 shington), Maaz Bin Safeer Ahmad and Vladimir Kim (Adobe), and Adriana Sch
 ulz (University of Washington)\n---------------------\nCLIP-Guided StyleGA
 N Inversion for Text-Driven Real Image Editing\n\nResearchers have recentl
 y begun exploring the use of StyleGAN-based models for real image editing.
  One particularly interesting application is using natural language descri
 ptions to guide the editing process. Existing approaches for editing image
 s using language either resort to instance-level laten...\n\n\nAbdul Basit
  Anees and Ahmet Canberk Baykal (Koç University), Duygu Ceylan (Adobe Rese
 arch), Erkut Erdem (Hacettepe University), and Aykut Erdem and Deniz Yuret
  (Koç University)\n---------------------\nSubspace-Preconditioned GPU Proj
 ective Dynamics with Contact for Cloth Simulation\n\nWe propose an efficie
 nt cloth simulation method that combines the merits of two drastically dif
 ferent numerical procedures, namely the subspace integration and paralleli
 zable iterative relaxation. We show those two methods can be organically c
 oupled within the framework of projective dynamics (PD), ...\n\n\nXuan Li 
 (UCLA); Yu Fang (UCLA, University of Pennsylvania); Lei Lan (University of
  Utah); Huamin Wang (Style 3D Research); Yin Yang (University of Utah, Sty
 le 3D Research); Minchen Li (UCLA, Carnegie Mellon University); and Chenfa
 nfu Jiang (UCLA, Style 3D Research)\n---------------------\nPerceptual Req
 uirements for World-Locked Rendering in AR and VR\n\nStereoscopic, head-tr
 acked display systems can show users realistic, world-locked virtual objec
 ts and environments. However, discrepancies between the rendering pipeline
  and physical viewing conditions can lead to perceived instability in the 
 rendered content resulting in reduced realism, immersion,...\n\n\nPhillip 
 Guan, Eric Penner, Joel Hegland, Benjamin Letham, and Douglas Lanman (Meta
  Reality Labs Research)\n---------------------\nNeural-Singular-Hessian: I
 mplicit Neural Representation of Unoriented Point Clouds by Enforcing Sing
 ular Hessian\n\nNeural implicit representation is a promising approach for
  reconstructing surfaces from point clouds. Existing methods combine vario
 us regularization terms to enforce the learned neural function to possess 
 the properties of a SDF, such as the Eikonal term and Laplacian energy ter
 m. However, when the...\n\n\nZixiong Wang, Yunxiao Zhang, and Rui Xu (Shan
 dong University); Fan Zhang (Shandong Technology and Business University);
  Peng-Shuai Wang (Peking University); Shuangmin Chen (Qingdao University o
 f Science and Technology); Shiqing Xin (Shandong University); Wenping Wang
  (Texas A&M University); and Changhe Tu (Shandong University)\n-----------
 ----------\nNeural Metamaterial Networks for Nonlinear Material Design\n\n
 Nonlinear metamaterials with tailored mechanical properties have applicati
 ons in engineering, medicine, robotics, and beyond. While modeling\ntheir 
 macromechanical behavior is challenging in itself, finding structure\npara
 meters that lead to an ideal approximation of high-level performance goals
 \nis a ...\n\n\nYue Li, Stelian Coros, and Bernhard Thomaszewski (ETH Züri
 ch)\n---------------------\nJoint UV Optimization and Texture Baking\n\nLe
 vel of detail (LOD) has been widely used in interactive computer graphics.
  In current industrial 3D modeling pipelines, artists rely on commercial s
 oftware to generate highly detailed models with UV maps, and then bake tex
 tures for low-poly counterparts. In these pipelines, each step is performe
 d ...\n\n\nJulian Knodt, Zherong Pan, Kui Wu, and Xifeng Gao (LightSpeed S
 tudios)\n---------------------\nCompact Neural Graphic Primitives with Lea
 rned Hash Probing\n\nNeural graphics primitives are faster and achieve hig
 her quality when their neural networks are augmented by spatial data struc
 tures that hold trainable features arranged in a grid. However, existing f
 eature grids either come with a large memory footprint (dense or factorize
 d grids, trees, and hash ...\n\n\nTowaki Takikawa (NVIDIA, University of T
 oronto); Thomas Müller, Merlin Nimier-David, and Alex Evans (NVIDIA); Sanj
 a Fidler (NVIDIA, University of Toronto); Alec Jacobson (University of Tor
 onto, Adobe Research); and Alexander Keller (NVIDIA)\n--------------------
 -\nFuseSR: Super Resolution for Real-time Rendering through Efficient Mult
 i-resolution Fusion\n\nThe workload of real-time rendering is steeply incr
 easing as the demand for high resolution, high refresh rates, and high rea
 lism rises, overwhelming most graphics cards. To mitigate this problem, on
 e of the most popular solutions is to render images at a low resolution to
  reduce rendering overhead,...\n\n\nZhihua Zhong (State Key Lab of CAD&CG,
  Zhejiang University; Zhejiang University City College); Jingsen Zhu (Stat
 e Key Lab of CAD&CG, Zhejiang University); Yuxin Dai (Zhejiang A&F Univers
 ity); Chuankun Zheng (State Key Lab of CAD&CG, Zhejiang University); Guanl
 in Chen (Zhejiang University City College); Yuchi Huo (Zhejiang Lab; State
  Key Lab of CAD&CG, Zhejiang University); and Hujun Bao and Rui Wang (Stat
 e Key Lab of CAD&CG, Zhejiang University)\n---------------------\nSparse S
 tress Structures from Optimal Geometric Measures\n\nIdentifying optimal st
 ructural designs given loads and constraints is a primary challenge in top
 ology optimization and shape optimization.  We propose a novel approach to
  this problem by finding a minimal tensegrity structure—a network of cable
 s and struts in equilibrium with a given loading f...\n\n\nDylan Rowe and 
 Albert Chern (University of California San Diego)\n---------------------\n
 Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Do
 uble Covering\n\nIn this paper, we propose a new method, called DoubleCove
 rUDF, for extracting the zero level-set from unsigned distance fields (UDF
 s). DoubleCoverUDF takes a learned UDF and a user-specified parameter r (a
  small positive real number) as input and extracts an iso-surface with an 
 iso-value r using the...\n\n\nFei Hou (Institute of Software, Chinese Acad
 emy of Sciences; University of Chinese Academy of Sciences); Xuhui Chen an
 d Wencheng Wang (Institute of Software, Chinese Academy Of Sciences; Unive
 rsity of Chinese Academy of Sciences); Hong Qin (Stony Brook University); 
 and Ying He (Nanyang Technological University)\n---------------------\nFLA
 RE: Fast Learning of Animatable and Relightable Mesh Avatars\n\nOur goal i
 s to efficiently learn personalized animatable 3D head avatars from videos
  that are geometrically accurate, realistic, relightable, and compatible w
 ith current rendering systems. While 3D meshes enable efficient processing
  and are highly portable, they lack realism in terms of shape and ap...\n\
 n\nShrisha Bharadwaj (Max Planck Institute for Intelligent Systems); Yufen
 g Zheng (ETH Zürich, Max Planck Institute for Intelligent Systems); Otmar 
 Hilliges (ETH Zürich); and Michael Black and Victoria Fernandez Abrevaya (
 Max Planck Institute for Intelligent Systems)\n---------------------\nComp
 utational Design of Wiring Layout on Tight Suits with Minimal Motion Resis
 tance\n\nAn increasing number of electronics are directly embedded on the 
 clothing to monitor human status (skeletal motion or electromyogram activi
 ty) or provide haptic feedback.\nA specific challenge to prototype and fab
 ricate such a clothing is to design the wiring layout, to minimize the int
 ervention to h...\n\n\nKai Wang, Xiaoyu Xu, Yinping Zheng, Da Zhou, and Sh
 ihui Guo (Xiamen University); Yipeng Qin (School of Computer Science and I
 nformatic, Cardiff University); and Xiaohu Guo (University of Texas at Dal
 las)\n---------------------\nDreamEditor: Text-Driven 3D Scene Editing wit
 h Neural Fields\n\nNeural fields have achieved impressive advancements in 
 view synthesis and scene reconstruction. However, editing these neural fie
 lds remains challenging due to the implicit encoding of geometry and textu
 re information. In this paper, we propose DreamEditor, a novel framework t
 hat enables users to pe...\n\n\nJingyu Zhuang (Sun Yat-sen University); Ch
 en Wang (University of Pennsylvania, Tsinghua University); Liang Lin (Sun 
 Yat-sen University); Lingjie Liu (University of Pennsylvania); and Guanbin
  Li (Sun Yat-sen University)\n---------------------\nPerceptual error opti
 mization for Monte Carlo animation rendering\n\nIndependently estimating i
 ndividual pixel values in Monte Carlo rendering results in a perceptually 
 sub-optimal white-noise distribution of error in image space. Recent works
  have shown that perceptual fidelity can be improved significantly by dist
 ributing pixel error as blue noise instead. Most suc...\n\n\nMiša Korać (S
 aarland University, DFKI); Corentin Salaün (Max Planck Institute for Infor
 matics); Iliyan Georgiev (Adobe); Pascal Grittmann (Saarland University); 
 Philipp Slusallek (Saarland University, DFKI); and Karol Myszkowski and Gu
 rprit Singh (Max Planck Institute for Informatics)\n---------------------\
 nA Physically-inspired Approach to the Simulation of Plant Wilting\n\nPlan
 ts are among the most complex objects to be modeled in computer graphics. 
 While a large body of work is concerned with structural modeling and the d
 ynamic reaction to external forces, our work focuses on the dynamic deform
 ation caused by plant internal wilting processes. To this end, we motivate
 ...\n\n\nFilippo Maggioli (Sapienza - University of Rome), Jonathan Klein 
 and Torsten Hädrich (KAUST), Emanuele Rodolà (Sapienza - University of Rom
 e), Wojtek Pałubicki (AMU), Sören Pirk (CAU), and Dominik L. Michels (KAUS
 T)\n---------------------\nReconstructing Close Human Interaction from Mul
 tiple Views\n\nThis paper addresses the challenging task of reconstructing
  the poses of multiple individuals engaged in close interactions, captured
  by multiple calibrated cameras. The difficulty arises from the noisy or f
 alse 2D keypoint detection due to inter-person occlusion, the heavy ambigu
 ity to associate ke...\n\n\nQing Shuai (Zhejiang University); Zhiyuan Yu (
 Department of Mathematics, Hong Kong University of Science and Technology)
 ; Zhize Zhou (Capital University of Physical Education and Sports); Lixin 
 Fan and Haijun Yang (WeBank); Can Yang (Department of Mathematics, Hong Ko
 ng University of Science and Technology); and Xiaowei Zhou (State Key Labo
 ratory of CAD&CG, Zhejiang Univerisity)\n---------------------\nAn Implici
 t Physical Face Model Driven by Expression and Style\n\n3D facial animatio
 n is often produced by manipulating facial deformation models (or rigs), t
 hat are traditionally parameterized by expression controls. A key componen
 t that is usually overlooked is expression ``style", as in, how a particul
 ar expression is performed. Although it is common to define ...\n\n\nLingc
 hen Yang (ETH Zürich); Gaspard Zoss and Prashanth Chandran (The Walt Disne
 y Company (Switzerland) GmbH); Paulo Gotardo (Disney Research Studios, The
  Walt Disney Company (Switzerland) GmbH); Markus Gross (ETH Zürich, The Wa
 lt Disney Company (Switzerland) GmbH); Barbara Solenthaler (ETH Zürich); E
 ftychios Sifakis (University of Wisconsin Madison); and Derek Bradley (The
  Walt Disney Company (Switzerland) GmbH)\n---------------------\nDrivable 
 Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Dri
 ven by Sparse RGB-D Input\n\nClothing is an important part of human appear
 ance but challenging to model in photorealistic avatars. In this work we p
 resent avatars with dynamically moving loose clothing that can be faithful
 ly driven by sparse RGB-D inputs as well as body and face motion. We propo
 se a Neural Iterative Closest Poi...\n\n\nDonglai Xiang (Carnegie Mellon U
 niversity/Robotics Institute, Meta Reality Labs Research); Fabian Prada, Z
 he Cao, Kaiwen Guo, and Chenglei Wu (Meta Reality Labs Research); Jessica 
 Hodgins (Carnegie Mellon University); and Timur Bagautdinov (Meta Reality 
 Labs Research)\n---------------------\nDevelopable Quad Meshes and Contact
  Element Nets\n\nThe property of a surface being developable can be expres
 sed in different equivalent ways, by vanishing Gauss curvature, or by the 
 existence of isometric mappings to planar domains. Computational contribut
 ions to this topic range from special parametrizations to discrete-isometr
 ic mappings. However,...\n\n\nVictor Ceballos Inza and Florian Rist (KAUST
 ), Johannes Wallner (TU Graz), and Helmut Pottmann (KAUST)\n--------------
 -------\nSLANG.D: Fast, Modular and Differentiable Shader Programming\n\nW
 e introduce SLANG.D, a shading language that incorporates first-class auto
 matic differentiation support derived from the Slang language. The new sha
 ding language allows us to transform a Direct3D-based path tracer to be fu
 lly differentiable with minor modifications to existing code. SLANG.D enab
 les...\n\n\nSai Praveen Bangaru (MIT CSAIL), Lifan Wu (NVIDIA), Tzu-Mao Li
  (University of California San Diego), Jacob Munkberg (NVIDIA), Gilbert Be
 rnstein (University of Washington), Jonathan Ragan-Kelley (MIT CSAIL), Aar
 on Lefohn (NVIDIA), Fredo Durand (MIT CSAIL), and Yong He (NVIDIA)\n------
 ---------------\nRerender A Video: Zero-Shot Text-Guided Video-to-Video Tr
 anslation\n\nLarge text-to-image diffusion models have exhibited impressiv
 e proficiency in generating high-quality images. However, when applying th
 ese models to video domain, ensuring temporal consistency across video fra
 mes remains a formidable challenge.\nThis paper proposes a novel zero-shot
  text-guided video...\n\n\nShuai Yang, Yifan Zhou, Ziwei Liu, and Chen Cha
 nge Loy (Nanyang Technological University, Singapore)\n-------------------
 --\nClothCombo: Modeling Inter-Cloth Interaction for Draping Multi-Layered
  Clothes\n\nWe present ClothCombo, a pipeline to drape arbitrary combinati
 ons of clothes on 3D human models with varying body shapes and poses. Whil
 e existing learning-based approaches for draping clothes have shown promis
 ing results, multi-layered clothing remains challenging as it is non-trivi
 al to model inte...\n\n\nDohae Lee, Hyun Kang, and In-Kwon Lee (Yonsei Uni
 versity)\n---------------------\nDiscontinuity-Aware 2D Neural Fields\n\nN
 eural image representations offer the possibility of high-fidelity, compac
 t storage, and resolution-independent accuracy, providing an attractive al
 ternative to traditional pixel and grid-based representations.  \nHowever,
  coordinate neural networks fail to capture discontinuities present in the
  ima...\n\n\nYash Belhe (University of California San Diego); Michael Ghar
 bi, Matt Fisher, and Iliyan Georgiev (Adobe Inc.); and Ravi Ramamoorthi an
 d Tzu-Mao Li (University of California San Diego)\n---------------------\n
 Efficient Human Motion Reconstruction from Monocular Videos with Physical 
 Consistency Loss\n\nVision-only motion reconstruction from monocular video
 s often produces artifacts such as foot sliding and jittery motions. Exist
 ing physics-based methods typically either simplify the problem to focus s
 olely on feet-ground contacts, or reconstruct full-body contacts within a 
 physics simulator, neces...\n\n\nLin Cong and Philipp Ruppel (Universität 
 Hamburg), Yizhou Wang (Peking University), Xiang Pan (Diago Tech Company),
  and Norman Hendrich and Jianwei Zhang (Universität Hamburg)\n------------
 ---------\nDoppler Time-of-Flight Rendering\n\nWe introduce Doppler time-o
 f-flight (D-ToF) rendering, an extension of ToF rendering for dynamic scen
 es, with applications in simulating D-ToF cameras. D-ToF cameras use high-
 frequency modulation for illumination and exposure, and measure the Dopple
 r frequency shift to compute the velocity of dynami...\n\n\nJuhyeon Kim an
 d Wojciech Jarosz (Dartmouth College), Ioannis Gkioulekas (Carnegie Mellon
  University), and Adithya Pediredla (Dartmouth College)\n-----------------
 ----\nAnti-Aliased Neural Implicit Surfaces with Encoding Level of Detail\
 n\nWe present LoD-NeuS, an efficient neural representation for high-freque
 ncy geometry detail recovery and anti-aliased novel view rendering. Drawin
 g inspiration from voxel-based representations with the level of detail (L
 oD), we introduce a multi-scale tri-plane-based scene representation that 
 is capa...\n\n\nYiyu Zhuang (Nanjing University); Qi Zhang and Ying Feng (
 Tencent); Hao Zhu and Yao Yao (Nanjing University); Xiaoyu Li, Yan-Pei Cao
 , and Ying Shan (Tencent); and Xun Cao (Nanjing University)\n-------------
 --------\nScaNeRF: Scalable Bundle-Adjusting Neural Radiance Fields for La
 rge-Scale Scene Rendering\n\nHigh-quality large-scale scene rendering requ
 ires a scalable representation and accurate camera poses. This research co
 mbines tile-based hybrid neural fields with parallel distributive optimiza
 tion to improve bundle-adjusting neural radiance fields. The proposed meth
 od scales with a divide-and-conqu...\n\n\nXiuchao Wu (State Key Laboratory
  of CAD & CG, Zhejiang University); Jiamin Xu (Hangzhou Dianzi Univeristy)
 ; Xin Zhang (State Key Laboratory of CAD&CG, Zhejiang Univerisity); Hujun 
 Bao (State Key Laboratory of CAD & CG, Zhejiang University); Qixing Huang 
 (University of Texas at Austin); Yujun Shen (Ant Group); James Tompkin (Br
 own University); and Weiwei Xu (State Key Laboratory of CAD&CG, Zhejiang U
 niverisity)\n---------------------\nPerceptually Adaptive Real-Time Tone M
 apping\n\nTone mapping operators aim to remap content to a display's dynam
 ic range. Virtual reality is a popular new display modality that has signi
 ficant differences from other media, making the use of traditional tone ma
 pping techniques difficult. Moreover, real-time adaptive estimation of ton
 e curves that ...\n\n\nTaimoor Tariq (Meta, Università della Svizzera ital
 iana) and Nathan Matsuda, Eric Penner, Jerry Jia, Douglas Lanman, Ajit Nin
 an, and Alexandre Chapiro (Meta)\n---------------------\nTwinTex: Geometry
 -aware Texture Generation for Abstracted 3D Architectural Models\n\nCoarse
  architectural models are often generated at scales ranging from individua
 l buildings to scenes for downstream applications such as Digital Twin Cit
 y, Metaverse, LODs, etc. Such piece-wise planar models can be abstracted a
 s twins from 3D dense reconstructions. However, these models typically l..
 .\n\n\nWeidan Xiong, Hongqian Zhang, Botao Peng, Ziyu Hu, Yongli Wu, Jianw
 ei Guo, and Hui Huang (Shenzhen University)\n---------------------\nRT-Oct
 ree: Accelerate PlenOctree Rendering with Batched Regular Tracking and Neu
 ral Denoising for Real-time Neural Radiance Fields\n\nNeural Radiance Fiel
 ds (NeRF) has demonstrated its ability to generate high-quality synthesize
 d views. Nonetheless, due to its slow inference speed, there is a need to 
 explore faster inference methods. In this paper, we propose RT-Octree, whi
 ch uses batched regular tracking based on PlenOctree with ...\n\n\nZixi Sh
 u, Ran Yi, Yuqi Meng, Yutong Wu, and Lizhuang Ma (Shanghai Jiao Tong Unive
 rsity)\n---------------------\nTopology Guaranteed B-Spline Surface/Surfac
 e Intersection\n\nThe surface/surface intersection technique serves as one
  of the most fundamental functions in modern CAD systems. Despite the long
  research history and successful applications of surface intersection algo
 rithms in various CAD industrial software, challenges still exist in balan
 cing the computational...\n\n\nJieyin Yang and Xiaohong Jia (Key Laborator
 y of Mathematics Mechanization, Chinese Academy Of Sciences; University of
  Chinese Academy of Sciences) and Dong-Ming Yan (National Laboratory of Pa
 ttern Recognition, Institute of Automation, Chinese Academy of Sciences)\n
 ---------------------\nConstrained Delaunay Tetrahedrization: A Robust and
  Practical Approach\n\nWe present a numerically robust algorithm for compu
 ting the constrained Delaunay tetrahedrization (CDT) of a piecewise-linear
  complex, which has a 100% success rate on the 4408 valid models in the Th
 ingy10k dataset.\nWe build on the underlying theory of the well-known tetg
 en software, but use a float...\n\n\nLorenzo Diazzi (UNIMORE, CNR-IMATI: G
 ENOVA); Daniele Panozzo (NYU); Amir Vaxman (University of Edinburgh); and 
 Marco Attene (CNR-IMATI: GENOVA)\n---------------------\nSelf-Calibrating,
  Fully Differentiable NLOS Inverse Rendering\n\nExisting time-resolved non
 -line-of-sight (NLOS) imaging methods reconstruct hidden scenes by inverti
 ng the optical paths of indirect illumination measured at visible relay su
 rfaces. These methods are prone to reconstruction artifacts due to inversi
 on ambiguities and capture noise, which are typicall...\n\n\nKiseok Choi, 
 Inchul Kim, and Dongyoung Choi (Korea Advanced Institute of Science and Te
 chnology (KAIST)); Julio Marco and Diego Gutierrez (Universidad de Zaragoz
 a - I3A); and Min H. Kim (Korea Advanced Institute of Science and Technolo
 gy (KAIST))\n---------------------\nAdaptive Tracking of a Single-Rigid-Bo
 dy Character in Various Environments\n\nSince the introduction of DeepMimi
 c [Peng et al. 2018], subsequent research\nhas focused on expanding the re
 pertoire of simulated motions across various\nscenarios. In this study, we
  propose an alternative approach for this goal,\na deep reinforcement lear
 ning method based on the simulation of a single...\n\n\nTaesoo Kwon, Taeho
 ng Gu, Jaewon Ahn, and Yoonsang Lee (Hanyang University)\n----------------
 -----\nVR-NeRF: High-Fidelity Virtualized Walkable Spaces\n\nWe present an
  end-to-end system for the high-fidelity capture, model reconstruction and
  real-time rendering of walkable spaces in virtual reality using neural ra
 diance fields. To this end, we designed and built a custom multi-camera ri
 g to densely capture walkable spaces in high fidelity with multi-...\n\n\n
 Linning Xu (The Chinese University of Hong Kong, Meta); Vasu Agrawal, Will
 iam Laney, Tony Garcia, Aayush Bansal, Changil Kim, Samuel Rota Bulò, Lore
 nzo Porzi, Peter Kontschieder, and Aljaž Božič (Meta); Dahua Lin (The Chin
 ese University of Hong Kong); and Michael Zollhoefer and Christian Richard
 t (Meta)\n---------------------\nQuantum Ray Marching for Reformulating Li
 ght Transport Simulation\n\nThe use of quantum computers in computer graph
 ics has gained interest in recent years, especially for the application to
  rendering. The current state of the art in quantum rendering relies on Gr
 over's search for finding ray intersections in $O(\sqrt{M})$ for $M$ primi
 tives. This quantum approach is ...\n\n\nLogan Mosier (University of Water
 loo); Morgan McGuire (Roblox, University of Waterloo); and Toshiya Hachisu
 ka (University of Waterloo)\n---------------------\nInteraction-Driven Act
 ive 3D Reconstruction with Object Interiors\n\nWe introduce an active 3D r
 econstruction method, which integrates visual perception, robot-object int
 eraction, and 3D scanning to recover both the exterior and interior geomet
 ries of a target 3D object. Unlike other works in active vision which focu
 s on optimizing camera viewpoints to better investi...\n\n\nZihao Yan, Fub
 ao Su, Mingyang Wang, and Ruizhen Hu (Shenzhen University); Hao Zhang (Sim
 on Fraser University); and Hui Huang (Shenzhen University)\n--------------
 -------\nLow-Light Image Enhancement with Wavelet-based Diffusion Models\n
 \nDiffusion models have achieved promising results in image restoration ta
 sks, yet suffer from time-consuming, excessive computational resource cons
 umption, and unstable restoration. To address these issues, we propose a r
 obust and efficient Diffusion-based Low-Light image enhancement approach, 
 dubbed...\n\n\nHai Jiang (Sichuan University); Ao Luo and Haoqiang Fan (Me
 gvii); Songchen Han (Sichuan University); and Shuaicheng Liu (University o
 f Electronic Science and Technology of China, Megvii)\n-------------------
 --\nUVDoc: Neural Grid-based Document Unwarping\n\nRestoring the original,
  flat appearance of a printed document from casual photographs of bent and
  wrinkled pages is a common everyday problem. In this paper we propose a n
 ovel method for grid-based single-image document unwarping. Our method per
 forms geometric distortion correction via a fully convo...\n\n\nFloor Verh
 oeven, Tanguy Magne, and Olga Sorkine-Hornung (ETH Zurich)\n--------------
 -------\nAmortizing Samples in Physics-Based Inverse Rendering using ReSTI
 R\n\nRecently, great progress has been made in physics-based differentiabl
 e rendering. Existing differentiable rendering techniques typically focus 
 on static scenes, but during inverse rendering—a key application for diffe
 rentiable rendering—the scene is updated dynamically by each gradient s...
 \n\n\nYu-Chen Wang (University of California Irvine), Chris Wyman and Lifa
 n Wu (NVIDIA), and Shuang Zhao (University of California Irvine)\n--------
 -------------\nGroomGen: A High-Quality Generative Hair Model Using Hierar
 chical Latent Representations\n\nDespite recent successes in hair acquisit
 ion that fits a high-dimensional hair model to a specific input subject, g
 enerative hair models, which establish general embedding spaces for encodi
 ng, editing, and sampling diverse hairstyles, are way less explored. In th
 is paper, we present GroomGen, the fi...\n\n\nYuxiao Zhou (ETH Zürich), Me
 nglei Chai and Alessandro Pepe (Google Inc.), Markus Gross (ETH Zürich), a
 nd Thabo Beeler (Google Inc.)\n---------------------\nClose the Design-to-
 Manufacturing Gap in Computational Optics with a ’Real2Sim’ Learned Two-Ph
 oton Neural Lithography Simulator\n\nWe introduce neural lithography to ad
 dress the ‘design-to-manufacturing’ gap in computational optics. Computati
 onal optics with large design degrees of freedom enable advanced functiona
 lities and performance beyond traditional optics. However, the existing de
 sign approaches often overloo...\n\n\nCheng Zheng (MIT), Guangyuan Zhao (T
 he Chinese University of Hong Kong), and Peter So (MIT)\n-----------------
 ----\nSparsePoser: Real-time Full-body Motion Reconstruction from Sparse D
 ata\n\nAccurate and reliable human motion reconstruction is crucial for cr
 eating natural interactions of full-body avatars in Virtual Reality (VR) a
 nd entertainment applications. As the Metaverse and social applications ga
 in popularity, users are seeking cost-effective solutions to create full-b
 ody animati...\n\n\nJose Luis Ponton and Haoran Yun (Universitat Politècni
 ca de Catalunya (UPC)); Andreas Aristidou (University of Cyprus, CYENS Cen
 tre of Excellence); and Carlos Andujar and Nuria Pelechano (Universitat Po
 litècnica de Catalunya (UPC))\n---------------------\nMyStyle++: A Control
 lable Personalized Generative Prior\n\nIn this paper, we propose an approa
 ch to obtain a personalized generative prior with explicit control over a 
 set of attributes. We build upon MyStyle, a recently introduced method, th
 at tunes the weights of a pre-trained StyleGAN face generator on a few ima
 ges of an individual. This system allows sy...\n\n\nLibing Zeng (Texas A&M
  University), Lele Chen and Yi Xu (OPPO US Research Center), and Nima Kala
 ntari (Texas A&M University)\n---------------------\nGarmentCode: Programm
 ing Parametric Sewing Patterns\n\nGarment modeling is an essential task of
  the global apparel industry and a core part of digital human modeling. Re
 alistic representation of garments with valid sewing patterns is key to th
 eir accurate digital simulation and eventual fabrication. \nHowever, littl
 e-to-no computational tools provide sup...\n\n\nMaria Korosteleva and Olga
  Sorkine-Hornung (ETH Zurich)\n---------------------\nDepolarized Holograp
 hy with Polarization-multiplexing Metasurface\n\nThe evolution of computer
 -generated holography (CGH) algorithms has prompted significant improvemen
 ts in the performances of holographic displays. Nonetheless, they start to
  encounter a limited degree of freedom in CGH optimization and physical co
 nstraints stemming from the coherent nature of hologr...\n\n\nSeung-Woo Na
 m, Youngjin Kim, Dongyeon Kim, and Yoonchan Jeong (Seoul National Universi
 ty)\n---------------------\nLight-Efficient Holographic Illumination for C
 ontinuous-Wave Time-of-Flight Imaging\n\nTime-of-flight (TOF) cameras have
  seen widespread adoption in recent years across the entire spectrum of co
 mmodity devices. However, these devices are fundamentally limited by their
  dynamic range, struggling with saturation from nearby bright objects and 
 noisy depth from farther darker objects. In t...\n\n\nDorian Chan and Matt
 hew O'Toole (Carnegie Mellon University)\n---------------------\nExplorabl
 e Mesh Deformation Subspaces from Unstructured 3D Generative Models\n\nExp
 loring variations of 3D shapes is a time-consuming process in traditional 
 3D modeling tools. Deep generative models of 3D shapes often feature conti
 nuous latent spaces that can, in principle, be used to explore potential v
 ariations starting from a set of input shapes; in practice, doing so can b
 e...\n\n\nArman Maesumi (Brown University); Paul Guerrero, Vladimir Kim, a
 nd Matthew Fisher (Adobe Inc.); Siddhartha Chaudhuri (Adobe Inc.; Indian I
 nstitute of Technology (IIT), Bombay); Noam Aigerman (Adobe Inc.); and Dan
 iel Ritchie (Brown University)\n---------------------\nSubspace Mixed Fini
 te Elements for Real-Time Heterogeneous Elastodynamics\n\nReal-time elasto
 dynamic solvers are well-suited for the rapid simulation of ho\nmogeneous 
 elastic materials, with high-rates generally enabled by aggressive\nearly 
 termination of timestep solves. Unfortunately, the introduction of strong\
 ndomain heterogeneities can make these solvers slow to converge. ...\n\n\n
 Ty Trusty, Otman Benchekroun, and Eitan Grinspun (University of Toronto); 
 Danny M. Kaufman (Adobe, University of Toronto); and David I.W. Levin (Uni
 versity of Toronto)\n---------------------\nFace0: Instantaneously Conditi
 oning a Text-to-Image Model on a Face\n\nWe present Face0, a novel way to 
 instantaneously condition a text-to-image generation model on a face, in s
 ample time, without any optimization procedures such as fine-tuning or inv
 ersions. We augment a dataset of annotated images with embeddings of the i
 ncluded faces and train an image generation m...\n\n\nDani Valevski, Danny
  Lumen, Yossi Matias, and Yaniv Leviathan (Google Research)\n-------------
 --------\nControllable Group Choreography using Contrastive Diffusion\n\nM
 usic-driven group choreography poses a considerable challenge but holds si
 gnificant potential for a wide range of industrial applications. The abili
 ty to generate synchronized and visually appealing group dance motions tha
 t are aligned with music opens up opportunities in many fields such as ent
 ert...\n\n\nNhat Le and Tuong Do (AIOZ); Khoa Do (VNUHCM-University of Sci
 ence); Hien Nguyen, Erman Tjiputra, and Quang Tran (AIOZ); and Anh Nguyen 
 (University of Liverpool)\n---------------------\nShapeSonic: Sonifying Fi
 ngertip Interactions for Non-Visual Virtual Shape Perception\n\nFor sighte
 d users, computer graphics and virtual reality allow them to model and per
 ceive imaginary objects and worlds. However, these approaches are inaccess
 ible to blind and visually impaired (BVI) users, since they primarily rely
  on visual feedback. To this end, we introduce ShapeSonic, a system ...\n\
 n\nJialin Huang (George Mason University), Alexa Siu (Adobe Research), Ran
 a Hanocka (University of Chicago), and Yotam Gingold (George Mason Univers
 ity)\n---------------------\nSimpleNeRF: Regularizing Sparse Input Neural 
 Radiance Fields with Simpler Solutions\n\nNeural Radiance Fields (NeRF) sh
 ow impressive performance for the photo-realistic free-view rendering of s
 cenes. However, NeRFs require dense sampling of images in the given scene,
  and their performance degrades significantly when only a sparse set of vi
 ews are available. Researchers have found that...\n\n\nNagabhushan Somraj,
  Adithyan Karanayil, and Rajiv Soundararajan (Indian Institute of Science)
 \n---------------------\nDeepBasis: Hand-Held Single-Image SVBRDF Capture 
 via Two-Level Basis Material Model\n\nRecovering spatial-varying bi-direct
 ional reflectance distribution function (SVBRDF) from a single hand-held c
 aptured image has been a meaningful but challenging task in computer graph
 ics. Benefiting from the learned data priors, some previous methods can ut
 ilize the potential material correlations ...\n\n\nLi Wang, Lianghao Zhang
 , Fangzhou Gao, and Jiawan Zhang (Tianjin University)\n-------------------
 --\nOpenSVBRDF: A Database of Measured Spatially-Varying Reflectance\n\nWe
  present the first large-scale database of measured spatially-varying anis
 otropic reflectance, consisting of 1,000 high-quality near-planar SVBRDFs,
  spanning 9 material categories such as wood, fabric and metal. Each sampl
 e is captured in 15 minutes, and represented as a set of high-resolution t
 ex...\n\n\nXiaohe Ma, Xianmin Xu, Leyao Zhang, Kun Zhou, and Hongzhi Wu (S
 tate Key Laboratory of CAD&CG, Zhejiang Univerisity)\n--------------------
 -\nBreak-A-Scene: Extracting Multiple Concepts from a Single Image\n\nText
 -to-image model personalization aims to introduce a user-provided concept 
 to the model, allowing its synthesis in diverse contexts. However, current
  methods primarily focus on the case of learning a single concept from mul
 tiple images with variations in backgrounds and poses, and struggle when a
 ...\n\n\nOmri Avrahami (The Hebrew University of Jerusalem), Kfir Aberman 
 (Google Research), Ohad Fried (Reichman University), Daniel Cohen-Or (Tel 
 Aviv University), and Dani Lischinski (The Hebrew University of Jerusalem)
 \n---------------------\nSlippage-Preserving Reshaping of Human-Made 3D Co
 ntent\n\nArtists often need to reshape 3D models of human-made objects by 
 changing the relative proportions or scales of different model parts or el
 ements while preserving the look and structure of the inputs. Manually res
 haping inputs to satisfy these criteria is highly time-consuming; the edit
  in our tease...\n\n\nChrystiano Araújo (University of British Columbia); 
 Nicholas Vining (University of British Columbia, NVIDIA); and Silver Burla
 , Manuel Ruivo de Oliveira, Enrique Rosales, and Alla Sheffer (University 
 of British Columbia)\n---------------------\nIconShop: Text-Guided Vector 
 Icon Synthesis with Autoregressive Transformers\n\nScalable Vector Graphic
 s (SVG) is a popular vector image format that offers good support for inte
 ractivity and animation. Despite its appealing characteristics, creating c
 ustom SVG content can be challenging for users due to the steep learning c
 urve required to understand SVG grammars or get familia...\n\n\nRonghuan W
 u, Wanchao Su, Kede Ma, and Jing Liao (City University of Hong Kong)\n----
 -----------------\nAnything to Glyph: Artistic Font Synthesis via Text-to-
 Image Diffusion Model\n\nThe automatic generation of artistic fonts is a c
 hallenging task that attracts many research interests. Previous methods sp
 ecifically focus on glyph or texture style transfer. However, we often com
 e across creative fonts composed of objects in posters or logos. These fon
 ts have proven to be a challe...\n\n\nChangShuo Wang, Lei Wu, XiaoLe Liu, 
 and Xiang Li (Shandong University); Lei Meng (Shandong University, Shandon
 g Research Institute of Industrial Technology); and Xiangxu Meng (Shandong
  University)\n---------------------\nLock-free Vertex Clustering for Multi
 core Mesh Reduction\n\nModern data collection methods can capture represen
 tations of 3D objects at resolutions much greater than they can be discret
 ely rendered as an image. To improve the efficiency of storage, transmissi
 on, rendering, and editing of 3D models constructed from such data, it is 
 beneficial to first employ ...\n\n\nNima Fathollahi and Sean Chester (Univ
 ersity of Victoria)\n---------------------\nNeural Packing: from Visual Se
 nsing to Reinforcement Learning\n\nWe present a novel learning framework t
 o solve the transport-and-packing (TAP) problem in 3D. It constitutes a fu
 ll solution pipeline from partial observations of input objects via RGBD s
 ensing and recognition to final box placement, via robotic motion planning
 , to arrive at a compact packing in a t...\n\n\nJuzhan Xu (Shenzhen Univer
 sity), Minglun Gong (University of Guelph), Hao Zhang (Simon Fraser Univer
 sity), and Hui Huang and Ruizhen Hu (Shenzhen University)\n---------------
 ------\nEmotional Speech-Driven Animation with Content-Emotion Disentangle
 ment\n\nTo be widely adopted, 3D facial avatars need to be animated easily
 , realistically, and directly, from speech signals. While the best recent 
 methods generate 3D animations that are synchronized with the input audio,
  they largely ignore the impact of emotions on facial expressions. Instead
 , their focu...\n\n\nRadek Daněček (Max Planck Institute for Intelligent S
 ystems); Kiran Chhatre (KTH Royal Institute of Technology); Shashank Tripa
 thi, Yandong Wen, and Michael Black (Max Planck Institute for Intelligent 
 Systems); and Timo Bolkart (Max Planck Institut for Intelligent Systems)\n
 ---------------------\nEditing Motion Graphics Video via Motion Vectorizat
 ion and Transformation\n\nMotion graphics videos are widely used in Web de
 sign, digital advertising, animated logos and film title sequences, to cap
 ture a viewer's attention. But editing such video is challenging because t
 he video provides a low-level sequence of pixels and frames rather than hi
 gher-level structure such as t...\n\n\nSharon Zhang and Jiaju Ma (Stanford
  University); Daniel Ritchie (Brown University); Jiajun Wu (Stanford Unive
 rsity); and Maneesh Agrawala (Stanford University, Roblox)\n--------------
 -------\nObject Motion Guided Human Motion Synthesis\n\nModeling human beh
 aviors in contextual environments has a wide range of applications in char
 acter animation, embodied AI, VR/AR, and robotics. In real-world scenarios
 , humans frequently interact with the environment and manipulate various o
 bjects to complete daily tasks. In this work, we study the p...\n\n\nJiama
 n Li, Jiajun Wu, and Karen Liu (Stanford University)\n--------------------
 -\nSpatiotemporally Consistent HDR Indoor Lighting Estimation\n\nWe propos
 e a physically-motivated deep learning framework to solve a general versio
 n of the challenging indoor lighting estimation problem. Given a single LD
 R image with a depth map, our method predicts spatially consistent lightin
 g at any given image position. Particularly, when the input is an LDR...\n
 \n\nZhengqin Li (Meta, University of California San Diego); Yu Li and Mikh
 ail Okunev (Meta); Manmohan Chandraker (University of California San Diego
 ); and Zhao Dong (Meta)\n---------------------\nCollapsing Embedded Cell C
 omplexes for Safer Hexahedral Meshing\n\nWe present a set of operators to 
 perform modifications, in particular collapses and splits, in volumetric c
 ell complexes which are discretely embedded in a background mesh. Topologi
 cal integrity and geometric embedding validity are carefully maintained. W
 e apply these operators strategically to bloc...\n\n\nHendrik Brückler and
  Marcel Campen (Osnabrück University)\n---------------------\nStable Discr
 ete Bending by Analytic Eigensystem and Adaptive Orthotropic Geometric Sti
 ffness\n\nIn this paper, we address two limitations of dihedral angle base
 d discrete bending (DAB) models, i.e. the indefiniteness of their energy H
 essian and their vulnerability to geometry degeneracies. To tackle the ind
 efiniteness issue, we present novel analytic expressions for the eigensyst
 em of a DAB en...\n\n\nZhendong Wang (Style3D Research); Yin Yang (Univers
 ity of Utah, Style3D Research); and Huamin Wang (Style3D Research)\n------
 ---------------\nText-Guided Vector Graphics Customization\n\nVector graph
 ics are widely used in digital art and valued by designers for their scala
 bility and layer-wise topological properties. However, the creation and ed
 iting of vector graphics necessitate creativity and design expertise, lead
 ing to a time-consuming process. In this paper, we propose a novel...\n\n\
 nPeiying Zhang (City University of Hong Kong), Nanxuan Zhao (Adobe Researc
 h), and Jing Liao (City University of Hong Kong)\n---------------------\nR
 each For the Spheres: Tangency-aware surface reconstruction of SDFs\n\nSig
 ned distance fields (SDFs) are a widely utilized implicit surface represen
 tation that has applications in various fields such as computer graphics, 
 computer vision, and applied mathematics. Despite their frequent use, trad
 itional methods such as Marching Cubes and its variants often overlook fun
 d...\n\n\nSilvia Sellán (University of Toronto), Christopher Batty (Univer
 sity of Waterloo), and Oded Stein (University of Southern California)\n---
 ------------------\nExtraSS: A Framework for Joint Spatial Super Sampling 
 and Frame Extrapolation\n\nWe introduce ExtraSS, a novel framework that co
 mbines spatial super sampling and frame extrapolation to enhance real-time
  rendering performance. By integrating these techniques, our approach achi
 eves a balance between performance and quality, generating temporally stab
 le and high-quality, high-resol...\n\n\nSongyin Wu (University of Californ
 ia Santa Barbara); Sungye Kim (Intel Corporation); Zheng Zeng (University 
 of California, Santa Barbara); Deepak Vembar, Sangeeta Jha, and Anton Kapl
 anyan (Intel Corporation); and Ling-Qi Yan (University of California, Sant
 a Barbara)\n---------------------\nLiveNVS: Neural View Synthesis on Live 
 RGB-D Streams\n\nExisting real-time RGB-D reconstruction approaches, like 
 Kinect Fusion, lack real-time photo-realistic visualization. This is due t
 o noisy, oversmoothed or incomplete geometry and blurry textures which are
  fused from imperfect depth maps and camera poses. Recent neural rendering
  methods can overcome...\n\n\nLaura Fink (Friedrich-Alexander-Universität 
 Erlangen-Nürnberg, Fraunhofer IIS); Darius Rückert and Linus Franke (Fried
 rich-Alexander-Universität Erlangen-Nürnberg); Joachim Keinert (Fraunhofer
  IIS); and Marc Stamminger (Friedrich-Alexander-Universität Erlangen-Nürnb
 erg)\n---------------------\nDiscovering Fatigued Movements for Virtual Ch
 aracter Animation\n\nVirtual character animation and movement synthesis ha
 ve advanced rapidly during recent years, especially through a combination 
 of extensive motion capture datasets and machine learning. A remaining cha
 llenge is interactively simulating characters that fatigue when performing
  extended motions, which ...\n\n\nNoshaba Cheema (German Research Center f
 or Artificial Intelligence, Max-Planck Institute for Informatics); Rui Xu 
 (German Research Center for Artificial Intelligence, Saarland University);
  Nam Hee Kim and Perttu Hämäläinen (Aalto University); Vladislav Golyanik 
 and Marc Habermann (Max-Planck-Institut für Informatik); Christian Theobal
 t (Max-Planck-Institut für Informatik, Saarland University); and Philipp S
 lusallek (Saarland University, German Research Center for Artificial Intel
 ligence)\n---------------------\nThe Shortest Route Is Not Always the Fast
 est: Probability-Modeled Stereoscopic Eye Movement Completion Time in VR\n
 \nSpeed and consistency of target-shifting play a crucial role in human ab
 ility to perform complex tasks. Shifting our gaze between objects of inter
 est quickly and consistently requires changes both in depth and direction.
  Gaze changes in depth are driven by slow, inconsistent vergence movements
  which...\n\n\nBudmonde Duinkharjav and Benjamin Liang (New York Universit
 y), Anjul Patney and Rachel Brown (NVIDIA Research), and Qi Sun (New York 
 University)\n---------------------\n3D Bézier Guarding: Boundary-Conformin
 g Curved Tetrahedral Meshing\n\nWe present a method for the generation of 
 higher-order tetrahedral meshes. In contrast to previous methods, the curv
 ed tetrahedral elements are guaranteed to be free of degeneracies and inve
 rsions while conforming exactly to prescribed piecewise polynomial surface
 s, such as domain boundaries or mate...\n\n\nPayam Khanteimouri and Marcel
  Campen (Osnabrück University)\n---------------------\nBézier Spline Simpl
 ification Using Locally Integrated Error Metrics\n\nInspired by surface me
 sh simplification methods, we present a technique for reducing the number 
 of Bézier curves in a vector graphics while maintaining high fidelity. We 
 propose a curve-to-curve distance metric to repeatedly conduct local segme
 nt removal operations. By construction, we identify all ...\n\n\nSiqi Wang
  (New York University); Chenxi Liu (University of British Columbia); Danie
 le Panozzo and Denis Zorin (New York University); and Alec Jacobson (Unive
 rsity of Toronto, Adobe Research)\n---------------------\nAvatarStudio: Te
 xt-driven Editing of 3D Dynamic Human Head Avatars\n\nCapturing and editin
 g full head performances enables the creation of virtual characters with v
 arious applications such as extended reality and media production. The pas
 t few years witnessed a steep rise in the photorealism of human head avata
 rs. Such avatars can be controlled through different input...\n\n\nMohit M
 endiratta, Xingang Pan, Mohamed Elgharib, Kartik Teotia, and Mallikarjun B
  R (Max Planck Institute for Informatics); Ayush Tewari (MIT CSAIL); Vladi
 slav Golyanik (Max Planck Institute for Informatics); Adam Kortylewski (Ma
 x Planck Institute for Informatics, University of Freiburg); and Christian
  Theobalt (Max Planck Institute for Informatics)\n---------------------\nA
 uthoring and Simulating Meandering Rivers\n\nWe present a method for inter
 actively authoring and simulating meandering river networks. Starting from
  a terrain with an initial low-resolution network encoded as a directed gr
 aph, we simulate the evolution of the path of the different channels using
  a physically-based migration equation augmented ...\n\n\nAxel Paris (Univ
 ersité Claude Bernard Lyon, Adobe); Eric Guérin (LIRIS); Pauline Collon (U
 niversité de Lorraine); and Eric Galin (LIRIS)\n---------------------\nInp
 ut-Dependent Uncorrelated Weighting for Monte Carlo Denoising\n\nImage-spa
 ce denoising techniques have been widely employed in Monte Carlo rendering
 , typically blending neighboring pixel estimates using a denoising kernel.
  It is widely recognized that a kernel should be adapted to characteristic
 s of the input pixel estimates in order to ensure robustness to diver...\n
 \n\nJonghee Back (Gwangju Institute of Science and Technology), Binh-Son H
 ua (Trinity College Dublin), Toshiya Hachisuka (University of Waterloo), a
 nd Bochang Moon (Gwangju Institute of Science and Technology)\n-----------
 ----------\nMultisource Holography\n\nHolographic displays promise several
  benefits including high quality 3D imagery, accurate accommodation cues, 
 and compact form-factors. However, holography relies on coherent illuminat
 ion which can create undesirable speckle noise in the final image. Althoug
 h smooth phase holograms can be speckle-fr...\n\n\nGrace Kuo, Florian Schi
 ffers, Douglas Lanman, Oliver Cossairt, and Nathan Matsuda (Reality Labs R
 esearch, Meta)\n---------------------\nNeural Stress Fields for Reduced-or
 der Elastoplasticity and Fracture\n\nThe material point method (MPM) is a 
 versatile simulation framework for large-deformation elastoplasticity and 
 fracture. However, MPM's long runtime and large memory consumptions render
  it unsuitable for applications constrained by computation time and memory
  usage, e.g., virtual reality. To overcom...\n\n\nZeshun Zong and Xuan Li 
 (University of California Los Angeles); Minchen Li (University of Californ
 ia Los Angeles, Carnegie Mellon University); Maurizio M. Chiaramonte (Meta
  Reality Labs Research); Wojciech Matusik (MIT CSAIL); Eitan Grinspun (Uni
 versity of Toronto); Kevin Carlberg (Meta Reality Labs Research); Chenfanf
 u Jiang (University of California Los Angeles); and Peter Yichen Chen (MIT
  CSAIL)\n---------------------\nFast-MSX: Fast Multiple Scattering Approxi
 mation\n\nClassical microfacet theory suffers from energy loss on material
 s with high roughness due to the single bounce assumption of most microfac
 et models. When roughness is high, there is a large chance of multiple sca
 ttering occurring among the microfacets of the surface. Without explicitly
  modelling for...\n\n\nEnrique Rosales (Huawei) and Fatemeh Teimury, Joshu
 a Horacsek, Aria Salari, Xuebin Qin, Adi Bar-Lev, Xiaoqiang Zhe, and Ligan
 g Liu (Huawei Technologies)\n---------------------\nAn Implicitly Stable M
 ixture Model for Dynamic Multi-fluid Simulations\n\nParticle-based simulat
 ion has become increasingly popular in real-time applications due to its e
 fficiency and adaptability, especially in generating highly dynamic fluid 
 effects. Nevertheless, the swift and stable simulation of interactions bet
 ween distinct fluids continues to pose challenges for cu...\n\n\nYanrui Xu
  (University of Groningen, University of Science and Technology Beijing); 
 Xiaokun Wang (University of Science and Technology Beijing, Bournemouth Un
 iversity); Jiamin Wang, Chongming Song, Tiancheng Wang, and Yanlan Zhang (
 University of Science and Technology Beijing); Jian Chang and Jianjun Zhan
 g (Bournemouth University); Jiri Kosinka (University of Groningen); Alexan
 dru Telea (Utrecht University); and Xiaojuan Ban (University of Science an
 d Technology Beijing)\n---------------------\nIntrinsic Harmonization for 
 Illumination-Aware Image Compositing\n\nDespite significant advancements i
 n network-based image harmonization techniques, there still exists a domai
 n gap between training pairs and real-world composites encountered during 
 inference. Most existing methods are trained to reverse global edits made 
 on segmented image regions, which fail to ac...\n\n\nChris Careaga, S. Mah
 di H. Miangoleh, and Yağız Aksoy (Simon Fraser University)\n--------------
 -------\nAn Adaptive Fast-Multipole-Accelerated Hybrid Boundary Integral E
 quation Method for Accurate Diffusion Curves\n\nIn theory, diffusion curve
 s promise complex color gradations for infinite-resolution vector graphics
 . In practice, existing realizations suffer from poor scaling, discretizat
 ion artifacts, or insufficient support for rich boundary conditions. Previ
 ous applications of the boundary element method to d...\n\n\nSeungbae Bang
  (University of Toronto, Amazon); Kirill Serkh (University of Toronto); Od
 ed Stein (University of Southern California, MIT); and Alec Jacobson (Univ
 ersity of Toronto, Adobe)\n---------------------\nDigital 3D Smocking Desi
 gn\n\nWe develop an optimization-based method to model smocking, a surface
  embroidery technique that provides decorative geometric texturing while m
 aintaining stretch properties of the fabric. During smocking, multiple pai
 rs of points on the fabric are stitched together, creating non-manifold ge
 ometric fe...\n\n\nJing Ren, Aviv Segall, and Olga Sorkine-Hornung (ETH Zü
 rich)\n---------------------\nHolographic Near-eye Display with Real-time 
 Embedded Rendering\n\nWe present a wearable full-color holographic augment
 ed reality headset with binocular vision support and real-time embedded ho
 logram calculation. Contrarily to most previously proposed prototypes, our
  headset employs high-speed amplitude-only microdisplays and embeds a comp
 act and lightweight electr...\n\n\nAntonin Gilles and Pierre Le Gargasson 
 (Institute of Research and Technology b-com) and Grégory Hocquet and Patri
 ck Gioia (Orange Labs, Institute of Research and Technology b-com)\n------
 ---------------\nAdaptNet: Policy Adaptation for Physics-Based Character C
 ontrol\n\nMotivated by human’s ability to adapt skills in the learning of 
 new ones, this paper presents AdaptNet, an approach for modifying the late
 nt space of existing policies to allow new behaviors to be quickly learned
  from like tasks in comparison to learning from scratch. Building on top o
 f a give...\n\n\nPei Xu (Clemson University, Roblox); Kaixiang Xie (McGill
  University); Sheldon Andrews (École de technologie supérieure, Roblox); P
 aul G. Kry (McGill University); Michael Neff (University of California Dav
 is); Morgan McGuire (Roblox, University of Waterloo); Ioannis Karamouzas (
 University of California Riverside); and Victor Zordan (Roblox, Clemson Un
 iversity)\n---------------------\nVET: Visual Error Tomography for Point C
 loud Completion and High-Quality Neural Rendering\n\nIn the last few years
 , deep neural networks opened the doors for big advances in novel view syn
 thesis. Many of these approaches are based on a (coarse) proxy geometry ob
 tained by structure from motion algorithms. Small deficiencies in this pro
 xy can be fixed by neural rendering, but larger holes or ...\n\n\nLinus Fr
 anke, Darius Rückert, and Laura Fink (Friedrich-Alexander Universität Erla
 ngen-Nürnberg); Matthias Innmann (NavVis GmbH); and Marc Stamminger (Fried
 rich-Alexander Universität Erlangen-Nürnberg)\n---------------------\nSAME
 : Skeleton-Agnostic Motion Embedding for Character Animation\n\nLearning d
 eep neural networks on human motion data has become common in computer gra
 phics research, but the heterogeneity of available datasets poses challeng
 es for training large-scale networks. \nThis paper presents a framework th
 at allows us to solve various animation tasks in a skeleton-agnostic ...\n
 \n\nSunmin Lee, Taeho Kang, and Jungnam Park (Seoul National University); 
 Jehee Lee (NC Research, Seoul National University); and Jungdam Won (Seoul
  National University)\n---------------------\nReal-Time Reconstruction of 
 Fluid Flow under Unknown Disturbance\n\nWe present a framework that captur
 es sparse Lagrangian flow information from a volume of real liquid and rec
 onstructs its detailed kinematic information in real time. Our framework c
 an perform flow reconstruction even when the liquid is disturbed by an obj
 ect of unknown movement and shape. Through a...\n\n\nKinfung Chu (Tohoku U
 niversity); Jiawei Huang (Chuzhou University, Void Dimensions); and Hidema
 sa Takana and Yoshifumi Kitamura (Tohoku University)\n--------------------
 -\nText-Guided Synthesis of Eulerian Cinemagraphs\n\nWe introduce Text2Cin
 emagraph,  a fully automated method for creating cinemagraphs from text de
 scriptions - an especially challenging task when prompts feature imaginary
  elements and artistic styles, given the complexity of interpreting the se
 mantics and motions of these images. We focus on cinemagr...\n\n\nAniruddh
 a Mahapatra (Carnegie Mellon University); Aliaksandr Siarohin, Hsin-Ying L
 ee, and Sergey Tulyakov (Snap Inc.); and Jun-Yan Zhu (Carnegie Mellon Univ
 ersity)\n---------------------\nNeRFFaceLighting: Implicit and Disentangle
 d Face Lighting Representation Leveraging Generative Prior in Neural Radia
 nce Fields\n\n3D-aware portrait lighting control is an emerging and promis
 ing domain, thanks to the recent advance of generative adversarial network
 s and neural radiance fields. Existing solutions typically try to decouple
  the lighting from the geometry and appearance for disentangled control wi
 th an explicit lig...\n\n\nKaiwen Jiang (Institute of Computing Technology
 , Chinese Academy of Sciences; Beijing Jiaotong University); Shu-Yu Chen (
 Institute of Computing Technology, Chinese Academy of Sciences); Hongbo Fu
  (School of Creative Media, City University of Hong Kong); and Lin Gao (In
 stitute of Computing Technology, Chinese Academy of Sciences; University o
 f Chinese Academy of Sciences)\n---------------------\nAdaptive Shells for
  Efficient Neural Radiance Field Rendering\n\nNeural radiance fields achie
 ve unprecedented quality for novel view synthesis, but their volumetric fo
 rmulation remains expensive, requiring a huge number of samples to render 
 high-resolution images. Volumetric encodings are essential to represent fu
 zzy geometry such as foliage and hair, and they ar...\n\n\nZian Wang and T
 ianchang Shen (NVIDIA, University of Toronto); Merlin Nimier-David and Nic
 holas Sharp (NVIDIA); Jun Gao (NVIDIA, University of Toronto); Alexander K
 eller (NVIDIA); Sanja Fidler (NVIDIA, University of Toronto); and Thomas M
 üller and Zan Gojcic (NVIDIA)\n---------------------\nMatFusion: A Generat
 ive Diffusion Model for SVBRDF Capture\n\nWe formulate SVBRDF estimation f
 rom photographs as a diffusion task. To model the distribution of spatiall
 y varying materials, we first train a novel unconditional SVBRDF diffusion
  backbone model on a large set of 312,165 synthetic spatially varying mate
 rial exemplars.  This SVBRDF  diffusion backbo...\n\n\nSam Sartor and Piet
 er Peers (College of William & Mary)\n---------------------\nMeshes with S
 pherical Faces\n\nA truly Möbius invariant discrete surface theory must co
 nsider meshes where the transformation group acts on all of its elements, 
 including edges and faces. We therefore systematically describe so called 
 sphere meshes with spherical faces and circular arcs as edges. Driven by a
 spects important for m...\n\n\nMartin Kilian (TU Wien), Anthony Ramos Cisn
 eros (KAUST), Christian Müller (TU Wien), and Helmut Pottmann (KAUST)\n---
 ------------------\nComputational Design of Flexible Planar Microstructure
 s\n\nMechanical metamaterials enable customizing the elastic properties of
  physical objects by altering their fine-scale structure. A broad gamut of
  effective material properties can be produced even from a single fabricat
 ion material by optimizing the geometry of a periodic microstructure tilin
 g. Past w...\n\n\nZhan Zhang (University of California Davis); Christopher
  Brandt (1000shapes GmbH); Jean Jouve (University Grenoble Alpes Inria, CN
 RS, Grenoble INP, LJK); Yue Wang and Tian Chen (University of Houston); Ma
 rk Pauly (Ecole Polytechnique Fédérale de Lausanne); and Julian Panetta (U
 niversity of California Davis)\n---------------------\nConcept Decompositi
 on for Visual Exploration and Inspiration\n\nA creative idea is often born
  from transforming, combining, and modifying ideas from existing visual ex
 amples capturing various concepts.\nHowever, one cannot simply copy the co
 ncept as a whole, and inspiration is achieved by examining certain aspects
  of the concept. Hence, it is often necessary to s...\n\n\nYael Vinker (Te
 l Aviv University, Google Research); Andrey Voynov (Google Research); Dani
 el Cohen-Or (Tel Aviv University, Google Research); and Ariel Shamir (Reic
 hman University)\n---------------------\nPose and Skeleton-aware Neural IK
  for Pose and Motion Editing\n\nPosing a 3D character for film or game is 
 an iterative and laborious process where many control handles (e.g. joints
 ) need to be manipulated to achieve a compelling result.  Neural Inverse K
 inematics (IK) is a new type of IK that enables sparse control over a 3D c
 haracter pose, and leverages full bo...\n\n\nDhruv Agrawal (ETH Zürich, Di
 sneyResearch|Studios); Martin Guay, Jakob Buhmann, and Dominik Borer (Disn
 eyResearch|Studios); and Robert W. Sumner (DisneyResearch|Studios, ETH Zür
 ich)\n---------------------\nEXIM: A Hybrid Explicit-Implicit Representati
 on for Text-Guided 3D Shape Generation\n\nThis paper presents a new text-g
 uided technique for generating 3D shapes. The technique leverages a hybrid
  3D shape representation, combining the strengths of explicit and implicit
  representations. Specifically, the explicit stage controls the generated 
 topology of the 3D shape and allows local mani...\n\n\nZhengzhe Liu, Jingy
 u Hu, and Ka-Hei Hui (The Chinese University of Hong Kong); Xiaojuan Qi (T
 he University of Hong Kong); Daniel Cohen-Or (Tel-Aviv University); and Ch
 i-Wing Fu (The Chinese University of Hong Kong)\n---------------------\nMI
 PS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RG
 B-D Reconstruction\n\nWe introduce MIPS-Fusion, a robust and scalable onli
 ne RGB-D reconstruction method based on a novel neural implicit representa
 tion -- multi-implicit-submap. Different from existing neural RGB-D recons
 truction methods lacking either flexibility with a single neural map or sc
 alability due to extra sto...\n\n\nYijie Tang (National University of Defe
 nse Technology (NUDT)), Jiazhao Zhang (Peking University), Zhinan Yu (Nati
 onal University of Defense Technology (NUDT)), He Wang (Peking University)
 , and Kai Xu (National University of Defense Technology (NUDT))\n---------
 ------------\nNeural Spectro-polarimetric Fields\n\nThe spatial radiance d
 istribution modeling of any light ray within a scene has been extensively 
 explored for applications, including view synthesis. Spectrum and polariza
 tion — the wave properties of light — are often neglected due to their int
 egration into three RGB spectral bands and t...\n\n\nYoungchan Kim, Wonjoo
 n Jin, Sunghyun Cho, and Seung-Hwan Baek (POSTECH)\n---------------------\
 nCurl Noise Jittering\n\nWe propose a method for implicitly generating blu
 e noise point sets. Our method is based on the observations that curl nois
 e vector fields are volume-preserving and that jittering can be construed 
 as moving points along the streamlines of a vector field. We demonstrate t
 hat the volume preservation k...\n\n\nJ. Andreas Bærentzen and Jeppe Reval
 l Frisvad (Technical University of Denmark) and Jonàs Martínez (INRIA)\n--
 -------------------\nEMS: 3D Eyebrow Modeling from Single-view Images\n\nE
 yebrows play a critical role in facial expression and appearance. Although
  the 3D digitization of faces is well explored, less attention has been dr
 awn to 3D eyebrow modeling. In this work, we propose EMS, the first learni
 ng-based framework for single-view 3D eyebrow reconstruction. Following th
 e m...\n\n\nChenghong Li, Leyang Jin, and Yujian Zheng (The Chinese Univer
 sity of Hong Kong, Shenzhen); Yizhou Yu (The University of Hong Kong); and
  Xiaoguang Han (The Chinese University of Hong Kong, Shenzhen)\n----------
 -----------\nTexture Atlas Compression Based on Repeated Content Removal\n
 \nOptimizing the memory footprint of 3D models can have a major impact on 
 the user experiences during real-time rendering and streaming visualizatio
 n, where the major memory overhead lies in the high-resolution texture dat
 a. In this work, we propose a robust and automatic pipeline to content-awa
 re, lo...\n\n\nYuzhe Luo (State Key Laboratory of CAD & CG, Zhejiang Unive
 rsity; LIGHTSPEED STUDIOS); Xiaogang Jin (State Key Laboratory of CAD & CG
 , Zhejiang University); Zherong Pan and Kui Wu (LIGHTSPEED STUDIOS); Qilon
 g Kou and Xiajun Yang (Tencent Technology (Shenzhen) Co., LTD); and Xifeng
  Gao (LIGHTSPEED STUDIOS)\n---------------------\nDifferentiable Dynamic V
 isible-Light Tomography\n\nWe propose the first visible-light tomography s
 ystem for real-time acquisition and reconstruction of general temporally-v
 arying 3D phenomena. Using a single high-speed camera, a high-performance 
 LED array and optical fibers with a total length of 5km, we build a novel 
 acquisition setup with no mecha...\n\n\nKaizhang Kang, Zoubin Bi, Xiang Fe
 ng, Yican Dong, Kun Zhou, and Hongzhi Wu (State Key Laboratory of CAD&CG, 
 Zhejiang Univerisity)\n---------------------\nSAILOR: Synergizing Radiance
  and Occupancy Fields for Live Human Performance Capture\n\nImmersive user
  experiences in live VR/AR performances require a fast and accurate free-v
 iew rendering of the performers. Existing methods are mainly based on Pixe
 l-aligned Implicit Functions (PIFu) or Neural Radiance Fields (NeRF). Howe
 ver, while PIFu-based methods usually fail to produce photoreali...\n\n\nZ
 heng Dong (State Key Laboratory of CAD & CG, Zhejiang University); Ke Xu (
 City University of Hong Kong); Yaoan Gao (State Key Laboratory of CAD & CG
 , Zhejiang University); Qilin Sun (The Chinese University of Hong Kong, Sh
 enzhen); Hujun Bao and Weiwei Xu (State Key Laboratory of CAD & CG, Zhejia
 ng University); and Rynson W.H. Lau (City University of Hong Kong)\n------
 ---------------\nNodeGit: Diffing and Merging Node Graphs\n\nThe use of ve
 rsion control is pervasive in collaborative software projects. Version con
 trol systems are based on two primary operations: diffing two versions to 
 compute the change between them and merging two versions edited concurrent
 ly. Recent works provide solutions to diff and merge graphics ass...\n\n\n
 Eduardo Rinaldi (Ubisoft), Davide Sforza (Sapienza University of Rome), an
 d Fabio Pellacini (University of Modena and Reggio Emilia)\n--------------
 -------\nAniPortraitGAN: Animatable 3D Portrait Generation from 2D Image C
 ollections\n\nPrevious animatable 3D-aware GANs for human generation have 
 primarily focused on either the human head or full body. However, head-onl
 y videos are relatively uncommon in real life, and full body generation ty
 pically does not deal with facial expression control and still has challen
 ges in generating ...\n\n\nYue Wu (Hong Kong University of Science and Tec
 hnology), Sicheng Xu (Microsoft Research Asia), Jianfeng Xiang (Tsinghua U
 niversity), Fangyun Wei (Microsoft Research Asia), Qifeng Chen (Hong Kong 
 University of Science and Technology), and Jiaolong Yang and Xin Tong (Mic
 rosoft Research Asia)\n---------------------\nA Neural Space-Time Represen
 tation for Text-to-Image Personalization\n\nA key aspect of text-to-image 
 personalization methods is the manner in which the target concept is repre
 sented within the generative process. This choice greatly affects the visu
 al fidelity, downstream editability, and disk space needed to store the le
 arned concept. In this paper, we explore a new t...\n\n\nYuval Alaluf, Ela
 d Richardson, Gal Metzer, and Daniel Cohen-Or (Tel Aviv University)\n-----
 ----------------\nSecond-Order Finite Elements for Deformable Surfaces\n\n
 We present a computational framework for simulating deformable surfaces wi
 th second-order triangular finite elements. Our method develops numerical 
 schemes for discretizing stretching, shearing, and bending energies of def
 ormable surfaces in a second-order finite-element setting. In particular, 
 we i...\n\n\nQiqin Le (Shanghai Qi Zhi Institute); Yitong Deng (Stanford U
 niversity); Jiamu Bu (Tsinghua University); Bo Zhu (Georgia Institute of T
 echnology); and Tao Du (Tsinghua University, Shanghai Qi Zhi Institute)\n-
 --------------------\nSingle-Image 3D Human Digitization with Shape-guided
  Diffusion\n\nWe present an approach to generate a 360-degree view of a pe
 rson with a consistent, high-resolution appearance from a single input ima
 ge. NeRF and its variants typically require videos or images from differen
 t viewpoints. Most existing approaches taking monocular input either rely 
 on ground-truth 3D...\n\n\nBadour AlBahar (Kuwait University); Shunsuke Sa
 ito, Hung-Yu Tseng, Changil Kim, and Johannes Kopf (Meta); and Jia-Bin Hua
 ng (University of Maryland)\n---------------------\nA Locality-based Neura
 l Solver for Optical Motion Capture\n\nWe present a novel locality-based l
 earning method for cleaning and solving optical motion capture data. Given
  noisy marker data, we propose a new heterogeneous graph neural network wh
 ich treats markers and joints as different types of nodes, and uses graph 
 convolution operations to extract the local...\n\n\nXiaoyu Pan and Bowen Z
 heng (State Key Laboratory of CAD & CG, Zhejiang University; ZJU-Tencent G
 ame and Intelligent Graphics Innovation Technology Joint Lab); Xinwei Jian
 g, Guanglong Xu, Xianli Gu, and Jingxiang Li (Tencent Games Digital Conten
 t Technology Center); Qilong Kou (Tencent Technology (Shenzhen) Co., LTD);
  He Wang (University College London (UCL)); Tianjia Shao and Kun Zhou (Sta
 te Key Laboratory of CAD & CG, Zhejiang University); and Xiaogang Jin (Sta
 te Key Laboratory of CAD & CG, Zhejiang University; ZJU-Tencent Game and I
 ntelligent Graphics Innovation Technology Joint Lab)\n--------------------
 -\nNeural Field Convolutions by Repeated Differentiation\n\nNeural fields 
 are evolving towards a general-purpose continuous representation for visua
 l computing. Yet, despite their numerous appealing properties, they are ha
 rdly amenable to signal processing. As a remedy, we present a method to pe
 rform general continuous convolutions with general continuous si...\n\n\nN
 tumba Elie Nsampi, Adarsh Djeacoumar, and Hans-Peter Seidel (Max-Planck-In
 stitut für Informatik); Tobias Ritschel (University College London (UCL));
  and Thomas Leimkühler (Max-Planck-Institut für Informatik)\n-------------
 --------\nJoint Sampling and Optimisation for Inverse Rendering\n\nWhen de
 aling with difficult inverse problems such as inverse rendering, using Mon
 te Carlo estimated gradients to optimise parameters can slow down converge
 nce due to variance. Averaging many gradient samples in each iteration red
 uces this variance trivially. However, for problems that require thousa...
 \n\n\nMartin Balint, Karol Myszkowski, Hans-Peter Seidel, and Gurprit Sing
 h (Max Planck Institute for Informatics)\n---------------------\nManifold 
 Path Guiding for Importance Sampling Specular Chains\n\nComplex visual eff
 ects such as caustics are often produced by light paths containing multipl
 e consecutive specular vertices (dubbed specular chains), which pose a cha
 llenge to unbiased estimation in Monte Carlo rendering.\nIn this work, we 
 study the light transport behavior within a sub-path that is ...\n\n\nZhim
 in Fan (Nanjing University); Pengpei Hong (University of Utah); Jie Guo (N
 anjing University); Changqing Zou (Zhejiang Lab; State Key Lab of CAD&CG, 
 Zhejiang University); Yanwen Guo (Nanjing University); and Ling-Qi Yan (Un
 iversity of California, Santa Barbara)\n---------------------\nConditional
  Resampled Importance Sampling and ReSTIR\n\nRecent work on generalized re
 sampled importance sampling (GRIS) enables importance-sampled Monte Carlo 
 integration with random variable weights replacing the usual division by p
 robability density. This enables very flexible spatiotemporal sample reuse
 , even if neighboring samples (e.g., light paths)...\n\n\nMarkus Kettunen 
 and Daqi Lin (NVIDIA); Ravi Ramamoorthi (NVIDIA, University of California 
 San Diego); Thomas Bashford-Rogers (University of Warwick); and Chris Wyma
 n (NVIDIA)\n---------------------\nART-Owen Scrambling\n\nWe present a nov
 el algorithm for implementing Owen-scrambling, combining the generation an
 d distribution of the scrambling bits in a single self-contained compact p
 rocess.\nWe employ a context-free grammar to build a binary tree of symbol
 s, and equip each symbol with a scrambling code that affects al...\n\n\nAb
 dalla G. M. Ahmed (KAUST), Matt Pharr (NVIDIA), and Peter Wonka (KAUST)\n-
 --------------------\nSinMPI: Novel View Synthesis from a Single Image wit
 h Expanded Multiplane Images\n\nSingle-image novel view synthesis is a cha
 llenging and ongoing problem that aims to generate an infinite number of c
 onsistent views from a single input image. Although significant efforts ha
 ve been made to advance the quality of generated novel views, less attenti
 on has been paid to the expansion of...\n\n\nGuo Pu, Peng-Shuai Wang, and 
 Zhouhui Lian (Wangxuan Institute of Computer Technology, Peking University
 )\n---------------------\nCamP: Camera Preconditioning for Neural Radiance
  Fields\n\nNeural Radiance Fields (NeRF) can be optimized to obtain high-f
 idelity 3D scene reconstructions of objects and large-scale scenes. Howeve
 r, NeRFs require accurate camera parameters as input --- inaccurate camera
  parameters result in blurry renderings. Extrinsic and intrinsic camera pa
 rameters are us...\n\n\nKeunhong Park, Phillip Henzler, Ben Mildenhall, Jo
 nathan T. Barron, and Ricardo Martin-Brualla (Google Research)\n----------
 -----------\nReconstruction of Machine-Made Shapes from Bitmap Sketches\n\
 nWe propose a method of reconstructing 3D machine-made shapes from bitmap 
 sketches by separating an input image into individual patches and jointly 
 optimizing their geometry. \nWe rely on two main observations:\n(1) human 
 observers interpret sketches of man-made shapes as a collection of simple 
 geometr...\n\n\nIvan Puhachov (Universite de Montreal; Huawei Technologies
 , Canada); Cedric Martens (Universite de Montreal); Paul G. Kry (McGill Un
 iversity; Huawei Technologies, Canada); and Mikhail Bessmeltsev (Universit
 e de Montreal)\n---------------------\nInovis: Instant Novel-View Synthesi
 s\n\nNovel-view synthesis is an ill-posed problem in that it requires infe
 rence of previously unseen information. Recently, reviving the traditional
  field of image-based rendering, neural methods proved particularly suitab
 le for this interpolation/extrapolation task; however, they often require 
 a-priori ...\n\n\nMathias Harrer and Linus Franke (Friedrich-Alexander-Uni
 versität Erlangen-Nürnberg); Laura Fink (Friedrich-Alexander-Universität E
 rlangen-Nürnberg, Fraunhofer IIS); and Marc Stamminger and Tim Weyrich (Fr
 iedrich-Alexander-Universität Erlangen-Nürnberg)\n---------------------\nT
 ransparent Object Reconstruction via Implicit Differentiable Refraction Re
 ndering\n\nReconstructing the geometry of transparent objects has been a l
 ong-standing challenge. Existing methods rely on complex setups, such as m
 anual annotation or darkroom conditions, to obtain object silhouettes and 
 usually require controlled environments with designed patterns to infer ra
 y-background co...\n\n\nFangzhou Gao, Lianghao Zhang, Li Wang, Jiamin Chen
 g, and Jiawan Zhang (Tianjin University)\n---------------------\nNon-Newto
 nian ViRheometry via Similarity Analysis\n\nWe estimate the three Herschel
 –Bulkley parameters (yield stress, power law index, and consistency parame
 ter) for shear-dependent fluid-like materials possibly with large-scale in
 clusions, for which rheometers may fail to provide a useful measurement. W
 e perform experiments using the unknown ma...\n\n\nMitsuki Hamamichi (Aoya
 ma Gakuin University); Kentaro Nagasawa and Masato Okada (The University o
 f Tokyo); Ryohei Seto (Wenzhou Institute, University of Chinese Academy of
  Sciences; Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vis
 ion and Brain Health)); and Yonghao Yue (Aoyama Gakuin University)\n------
 ---------------\nDiffusion-based Holistic Texture Rectification and Synthe
 sis\n\nWe present a novel framework for rectifying occlusions and distorti
 ons in degraded texture samples from natural images. Traditional texture s
 ynthesis approaches focus on generating textures from pristine samples, wh
 ich necessitate meticulous preparation by humans and are often unattainabl
 e in most n...\n\n\nGuoqing Hao (University of Tsukuba, National Institute
  of Advanced Industrial Science and Technology); Satoshi Iizuka (Universit
 y of Tsukuba); Kensho Hara (National Institute of Advanced Industrial Scie
 nce); Edgar Simo-Serra (Waseda University); Hirokatsu Kataoka (National In
 stitute of Advanced Industrial Science); and Kazuhiro Fukui (University of
  Tsukuba)\n---------------------\nA Neural Implicit Representation for the
  Image Stack: Depth, All in Focus, and High Dynamic Range\n\nIn everyday p
 hotography, physical limitations of camera sensors and lenses frequently l
 ead to a variety of degradations in captured images such as saturation or 
 defocus blur. A common approach to overcome these limitations is to resort
  to image stack fusion, which involves capturing multiple images ...\n\n\n
 Chao Wang (Max-Planck-Institut für Informatik); Ana Serrano (Universidad d
 e Zaragoza); and Xingang Pan, Bin Chen, Hans-Peter Seidel, Karol Myszkowsk
 i, Christian Theobalt, Krzysztof Wolski, and Thomas Leimkühler (Max-Planck
 -Institut für Informatik)\n---------------------\nPower Plastics: A Hybrid
  Lagrangian/Eulerian Solver for Mesoscale Inelastic Flows\n\nWe propose a 
 novel hybrid Lagrangian/Eulerian method for simulating inelastic materials
  that generates high-quality particle distributions with strict volume con
 trol. At its core, our approach integrates an updated Lagrangian time disc
 retization of continuum mechanics with the Power Particle-In-Cell...\n\n\n
 Ziyin Qu (University of Pennsylvania, University of California Los Angeles
 ); Minchen Li (University of California Los Angeles, Carnegie Mellon Unive
 rsity); Yin Yang (University of Utah); Chenfanfu Jiang (University of Cali
 fornia Los Angeles); and Fernando de Goes (Pixar Animation Studios)\n-----
 ----------------\nSeamlessNeRF: Stitching Part NeRFs with Gradient Propaga
 tion\n\nNeural Radiance Fields (NeRFs) have emerged as a promising represe
 ntation for 3D scenes, sparking a surge in research aimed at extending the
  editing capabilities in this domain. The task of seamless editing and mer
 ging of different NeRFs, similar to the "copy-and-paste" function in 2D im
 age editing,...\n\n\nBingchen Gong and Yuehao Wang (The Chinese University
  of Hong Kong); Xiaoguang Han (Shenzhen Research Institute of Big Data, th
 e Chinese University of Hong Kong (Shenzhen)); and Qi Dou (The Chinese Uni
 versity of Hong Kong)\n---------------------\nCapturing Animation-Ready Is
 otropic Materials Using Systematic Poking\n\nCapturing material properties
  of real-world elastic solids is both challenging and highly relevant to m
 any applications in computer graphics, robotics and related fields. We giv
 e a non-intrusive, in-situ and inexpensive approach to measure the nonline
 ar elastic energy density function of man-made ma...\n\n\nHuanyu Chen, Dan
 yong Zhao, and Jernej Barbic (University of Southern California)\n--------
 -------------\nLitNeRF: Intrinsic Radiance Decomposition for High-Quality 
 View Synthesis and Relighting of Faces\n\nHigh-fidelity, photorealistic 3D
  capture of a human face is a long-standing problem in computer graphics -
 - the complex material of skin, intricate geometry of hair, and fine scale
  textural details make it challenging. Traditional techniques rely on very
  large and expensive capture rigs to reconstru...\n\n\nKripasindhu Sarkar 
 (Google Inc.); Marcel Bühler and Simon Li (ETH Zürich, Google Inc.); and D
 aoye Wang, Delio Vicini, Jérémy Riviere, Yinda Zhang, Sergio Orts-Escolano
 , Paulo Gotardo, Thabo Beeler, and Abhimitra Meka (Google Inc.)\n---------
 ------------\nProjective Sampling for Differentiable Rendering of Geometry
 \n\nDiscontinuous visibility changes at object boundaries remain a persist
 ent source of difficulty in the area of differentiable rendering. Left unt
 reated, they bias computed gradients so severely that even basic optimizat
 ion tasks fail.\n\nPrior path-space methods addressed this bias by decoupl
 ing bounda...\n\n\nZiyi Zhang, Nicolas Roussel, and Wenzel Jakob (Ecole Po
 lytechnique Fédérale de Lausanne)\n---------------------\nAnimating Street
  View\n\nWe present a system that automatically brings street view imagery
  to life by populating it with naturally behaving, animated pedestrians an
 d vehicles. Our approach is to remove existing people and vehicles from th
 e input image, insert moving objects with proper scale, angle, motion and 
 appearance, p...\n\n\nMengyi Shan, Brian Curless, Ira Kemelmacher-Shlizerm
 an, and Steve Seitz (University of Washington)\n---------------------\nCom
 putational Design of LEGO Sketch Art\n\nThis paper presents computational 
 methods to aid the creation of LEGO Sketch models from simple input images
 . Beyond conventional LEGO mosaics, we aim to improve the expressiveness o
 f LEGO models by utilizing LEGO tiles with sloping and rounding edges, tog
 ether with rectangular bricks, to reproduce ...\n\n\nMingjun Zhou (The Chi
 nese University of Hong Kong); Jiahao Ge (The Chinese University of Hong K
 ong, Qianzhi Technology Inc.); Hao Xu (Qianzhi Technology Inc.); and Chi-W
 ing Fu (The Chinese University of Hong Kong)\n---------------------\nLearn
 ing Gradient Fields for Scalable and Generalizable Irregular Packing\n\nTh
 e packing problem, also known as cutting or nesting, has diverse applicati
 ons in logistics, manufacturing, layout design, and atlas generation. It i
 nvolves arranging irregularly shaped pieces to minimize waste while avoidi
 ng overlap. Recent advances in machine learning, particularly reinforcemen
 t ...\n\n\nTianyang Xue (Shandong University), Mingdong Wu (Peking Univers
 ity), Lin Lu and Haoxuan Wang (Shandong University), and Hao Dong and Baoq
 uan Chen (Peking University)\n---------------------\nEfficient Visualizati
 on of Light Pollution for the Night Sky\n\nThe artificial light sources ma
 ke our daily life convenient, but they cause a serious problem called ligh
 t pollution. \nWe propose a system for efficient visualization of the ligh
 t pollution for the night sky.\nA number of methods have been proposed for
  rendering the sky, but most of the methods focus...\n\n\nYoshinori Dobash
 i and Naoto Ishikawa (Hokkaido University, Prometech CG Research) and Kei 
 Iwasaki (Saitama University, Prometech CG Research)\n---------------------
 \nDecaf: Monocular Deformation Capture for Face and Hand Interactions\n\nE
 xisting methods for 3D tracking from monocular RGB videos predominantly co
 nsider articulated and rigid objects (e.g., two hands or humans interactin
 g with rigid environments).  Modelling dense non-rigid object deformations
  in this setting (e.g., when hand are interacting with a face), remained l
 arg...\n\n\nSoshi Shimada (Max-Planck-Institut für Informatik; Saarbrücken
  Research Center for Visual Computing, Interaction and Artificial  Intelli
 gence); Vladislav Golyanik (Max-Planck-Institut für Informatik); Patrick P
 érez (Valeo); and Christian Theobalt (Max-Planck-Institut für Informatik; 
 Saarbrücken Research Center for Visual Computing, Interaction and Artifici
 al  Intelligence)\n---------------------\nExtended Path Space Manifolds fo
 r Physically Based Differentiable Rendering\n\nPhysically based differenti
 able rendering has become an increasingly important topic in recent years.
  A common pipeline computes local color derivatives of light paths or pixe
 ls with respect to arbitrary scene parameters, and enables optimizing or r
 ecovering the scene parameters through iterative gr...\n\n\nJiankai Xing a
 nd Xuejun Hu (Tsinghua University), Fujun Luan (Adobe Research), Ling-Qi Y
 an (University of California Santa Barbara), and Kun Xu (Tsinghua Universi
 ty)\n---------------------\nMultiple-bounce Smith Microfacet BRDFs using t
 he Invariance Principle\n\nSmith microfacet models are widely used in comp
 uter graphics to represent materials. Traditional microfacet models do not
  consider the multiple bounces on microgeometries, leading to visible ener
 gy missing, especially on rough surfaces. Later, as the equivalence betwee
 n the microfacets and volume ha...\n\n\nYuang Cui (Anhui Science and Techn
 ology University); Gaole Pan and Jian Yang (Nanjing University of Science 
 and Technology); Lei Zhang (The Hong Kong Polytechnic University); Ling-Qi
  Yan (University of California, University of California Santa Barbara); a
 nd Beibei Wang (Nankai University, Nanjing University of Science and Techn
 ology)\n---------------------\nAn Architecture and Implementation of Real-
 Time Sound Propagation Hardware for Mobile Devices\n\nThis paper presents 
 a high-performance and low-power hardware architecture for real-time sound
  rendering on mobile devices. Traditional sound rendering algorithms requi
 re high-performance CPUs or GPUs for processing because of its high comput
 ational complexities to realize ultra-realistic 3D audio. ...\n\n\nEUNJAE 
 KIM, SUKWON CHOI, and JIYOUNG KIM (Sejong University, Sejongpia); JAE-HO N
 AH (Sangmyung Univesrity); WOONAM JUNG (Sejongpia); TAE-HYEONG LEE (Sejong
  University); YEON-KUG MOON (Korea Electronics Technology Institute); and 
 WOO-CHAN PARK (Sejong University, Sejongpia)\n---------------------\nLearn
 ing Contact Deformations with General Collider Descriptors\n\nThis paper p
 resents a learning-based method for the simulation of rich contact deforma
 tions on reduced deformation models. Previous works learn deformation mode
 ls for specific pairs of objects, and we lift this limitation by designing
  a neural model that supports general rigid collider shapes. We do...\n\n\
 nCristian Romero and Dan Casas (Universidad Rey Juan Carlos) and Maurizio 
 Chiaramonte and Miguel A. Otaduy (Meta Reality Labs Research)\n-----------
 ----------\nConstructive Solid Geometry on Neural Signed Distance Fields\n
 \nSigned Distance Fields (SDFs) parameterized by neural networks have rece
 ntly gained popularity as a fundamental geometric representation. However,
  editing the shape encoded by a neural SDF remains an open challenge.  A t
 empting approach is to leverage common geometric operators (e.g., boolean 
 operat...\n\n\nZoë Marschner (Massachusetts Institute of Technology, Carne
 gie Mellon University); Silvia Sellán (University of Toronto); Hsueh-Ti D
 erek Liu (Roblox Research); and Alec Jacobson (University of Toronto)\n---
 ------------------\nProgressive Shell Quasistatics for Unstructured Meshes
 \n\nThin shell structures exhibit complex behaviors critical for modeling 
 and design across wide-ranging applications. To capture their mechanical r
 esponse requires finely detailed, high-resolution meshes. Corresponding si
 mulations for predicting equilibria with these meshes are expensive, where
 as coars...\n\n\nJiayi Eris Zhang (Stanford University, Adobe); Jérémie Du
 mas and Raymond Fei (Adobe); Alec Jacobson (University of Toronto, Adobe);
  Doug James (Stanford University); and Danny Kaufman (Adobe)\n------------
 ---------\nDiffusion Posterior Illumination for Ambiguity-aware Inverse Re
 ndering\n\nInverse rendering, the process of inferring scene properties fr
 om images, is a challenging inverse problem. The task is ill-posed, as man
 y different scene configurations can give rise to the same image. Most exi
 sting solutions incorporate priors into the inverse-rendering pipeline to 
 encourage plaus...\n\n\nLinjie Lyu (Max-Planck-Institut für Informatik), A
 yush Tewari (MIT CSAIL), Marc Habermann (Max-Planck-Institut für Informati
 k), Shunsuke Saito and Michael Zollhöfer (Reality Labs Research), and Thom
 as Leimkühler and Christian Theobalt (Max-Planck-Institut für Informatik)\
 n---------------------\nZero-Shot 3D Shape Correspondence\n\nWe propose a 
 novel zero-shot approach to computing correspondences\nbetween 3D shapes. 
 Existing approaches mainly focus on isometric and\nnear-isometric shape pa
 irs (e.g., human vs. human), but less attention has\nbeen given to strongl
 y non-isometric and inter-class shape matching (e.g., human vs. cow)...\n\
 n\nAhmed Abdelreheem and Abdelrahman Eldesokey (King Abdullah University o
 f Science and Technology (KAUST)), Maks Ovsjanikov (Centre National de la 
 Recherche Scientifique - Laboratoire d'informatique de l'École Polytechniq
 ue (LIX)), and Peter Wonka (King Abdullah University of Science and Techno
 logy (KAUST))\n---------------------\nMOCHA: Real-Time Motion Characteriza
 tion via Context Matching\n\nTransforming neutral, characterless input mot
 ions to embody the distinct style of a notable character in real time is h
 ighly compelling for character animation. This paper introduces MOCHA, a n
 ovel online motion characterization framework that transfers both motion s
 tyles and body proportions from a...\n\n\nDeok-Kyeong Jang (KAIST, MOVIN I
 nc.); Yuting Ye (Meta); Jungdam Won (Seoul National University); and Sung-
 Hee Lee (KAIST)\n---------------------\nNeural Point-based Volumetric Avat
 ar: Surface-guided Neural Points for Efficient and Photorealistic Volumetr
 ic Head Avatar\n\nRendering photo-realistic and vividly moving human heads
  is very important for pleasant and immersive experience in AR/VR and vide
 o conferencing. However, existing methods usually struggle to model challe
 nging facial regions (e.g., mouth interior, eyes, hair/beard), resulting i
 n unrealistic and blur...\n\n\nCong Wang (Tsinghua University); Di Kang, Y
 an-Pei Cao, Linchao Bao, and Ying Shan (Tencent); and Song-Hai Zhang (Tsin
 ghua University)\n---------------------\nSimultaneous Color Computer Gener
 ated Holography\n\nComputer generated holography has long been touted as t
 he future of augmented and virtual reality (AR/VR) displays, but has yet t
 o be realized in practice. Previous high-quality, color holographic displa
 ys have made either a 3x sacrifice on frame rate by using a sequential col
 or illumination scheme ...\n\n\nEric Markley, Nathan Matsuda, Florian Schi
 ffers, Oliver Coissart, and Grace Kuo (Meta)\n---------------------\nRepur
 posing Diffusion Inpainters for Novel View Synthesis\n\nIn this paper, we 
 present a method for generating consistent novel views from a single sourc
 e image. Our approach focuses on maximizing the reuse of visible pixels fr
 om the source view. To achieve this, we use a monocular depth estimator th
 at transfers visible pixels from the source view to the targ...\n\n\nYash 
 Kant (University of Toronto, Snap Inc.); Aliaksandr Siarohin, Michael Vasi
 lkovsky, Riza Alp Guler, Jian Ren, and Sergey Tulyakov (Snap Inc.); and Ig
 or Gilitschenski (University of Toronto)\n---------------------\nHigh-Reso
 lution Volumetric Reconstruction for Clothed Humans\n\nWe present a novel 
 method for reconstructing clothed humans from a sparse set of, e.g., 1-6 R
 GB images. We revisit the volumetric approach and demonstrate that better 
 performance can be achieved with proper system design. The volumetric repr
 esentation offers significant advantages in leveraging 3D s...\n\n\nSicong
  Tang (Simon Fraser University); Guangyuan Wang, Qing Ran, Lingzhi Li, and
  Li Shen (Alibaba); and Ping Tan (Simon Fraser University)\n--------------
 -------\nLiCROM: Linear-Subspace Continuous Reduced Order Modeling with Ne
 ural Fields\n\nLinear reduced-order modeling (ROM) simplifies complex simu
 lations by approximating the behavior of a system using a simplified kinem
 atic representation. Typically, ROM\nis trained on input simulations creat
 ed with a specific spatial discretization, \nand then serves to accelerate
  simulations with the...\n\n\nYue Chang (University of Toronto), Peter Yic
 hen Chen (MIT CSAIL), Zhecheng Wang (University of Toronto), Maurizio M. C
 hiaramonte and Kevin Carlberg (Meta Reality Labs Research), and Eitan Grin
 spun (University of Toronto)\n---------------------\nMCNeRF: Monte Carlo R
 endering and Denoising for Real-Time NeRFs\n\nThe volume rendering step us
 ed in Neural Radiance Fields (NeRFs) produces highly photorealistic result
 s, but is inherently slow because it evaluates an MLP at a large number of
  sample points per ray. Previous work has addressed this by either proposi
 ng neural scene representations that are faster to...\n\n\nKunal Gupta (UC
  San Diego); Milos Hasan, Zexiang Xu, Fujun Luan, Kalyan Sunkavalli, and X
 in Sun (Adobe Inc.); Manmohan Chandraker (UC San Diego); and Sai Bi (Adobe
  Inc.)\n---------------------\nNeural Collision Fields for Triangle Primit
 ives\n\nWe present neural collision fields as an alternative to contact po
 int sampling in physics simulations.\nOur approach is built on top of a no
 vel smoothed integral formulation for the contact surface patches between 
 two triangle meshes. By reformulating collisions as an integral, we avoid 
 issues of sam...\n\n\nRyan Zesch (Texas A&M University), Vismay Modi (Univ
 ersity of Toronto), Shinjiro Sueda (Texas A&M University), and David Levin
  (University of Toronto)\n---------------------\nLearning the Geodesic Emb
 edding with Graph Neural Networks\n\nWe present GeGnn, a learning-based me
 thod for computing the approximate geodesic distance between two arbitrary
  points on discrete polyhedra surfaces with constant time complexity after
  fast precomputation. Previous relevant methods either focus on computing 
 the geodesic distance between a single so...\n\n\nBo Pang (Peking Unversit
 y); Zhongtian Zheng (Peking University); Guoping Wang (Peking Unversity); 
 and Peng-Shuai Wang (Peking University, Wangxuan Institute of Computer Tec
 hnology)\n---------------------\nGroundLink: A Dataset Unifying Human Body
  Movement and Ground Reaction Dynamics\n\nThe physical plausibility of hum
 an motions is vital to various applications in the fields including but no
 t limited to graphics, animation, robotics, vision, biomechanics, and spor
 ts science. While fully simulating human motions with physics is an extrem
 e challenge, we hypothesize that we can treat ...\n\n\nXingjian Han, Ben S
 enderling, Stanley To, Deepak Kumar, and Emily Whiting (Boston University)
  and Jun Saito (Adobe Research)\n---------------------\nGARM-LS: A Gradien
 t-Augmented Reference-Map Method for Level-Set Fluid Simulation\n\nThis pa
 per presents a novel level-set method by combining gradient augmentation a
 nd reference mapping to enable high-fidelity interface tracking and surfac
 e tension flow simulation. At the center of our approach is a novel refere
 nce-map algorithm to concurrently convect level-set values and gradient...
 \n\n\nXingqiao Li (School of IST & National Key Lab. of AGI, Peking Univer
 sity); Xingyu Ni (School of CS & National Key Lab. of AGI, Peking Universi
 ty); Bo Zhu (Georgia Institute of Technology, Dartmouth College); Bin Wang
  (Beijing Institute for General Artificial Intelligence); and Baoquan Chen
  (School of IST & National Key Lab. of AGI, Peking University)\n----------
 -----------\nInteractive Story Visualization with Multiple Characters\n\nA
 ccurate Story visualization requires several necessary elements, such as i
 dentity consistency across frames, the alignment between plain text and vi
 sual content, and a reasonable layout of objects in images. Most previous 
 works endeavor to meet these requirements by fitting a text-to-image (T2I)
  mo...\n\n\nYuan Gong (Tsinghua University); Youxin Pang (MAIS & NLPR, Ins
 titute of Automation, Chinese Academy of Sciences, Beijing, China; School 
 of Artificial Intelligence, University of Chinese Academy of Sciences); Xi
 aodong Cun and Menghan Xia (Tencent); Yingqing He (Hong Kong University of
  Science and Technology); Haoxin Chen, Longyue Wang, Yong Zhang, Xintao Wa
 ng, and Ying Shan (Tencent); and Yujiu Yang (Tsinghua University)\n-------
 --------------\nDiffusing Colors: Image Colorization with Text Guided Diff
 usion\n\nThe colorization of grayscale images is a complex and subjective 
 task with significant challenges. Despite recent progress in employing lar
 ge-scale datasets with deep neural networks, difficulties with controllabi
 lity and visual quality persist. To tackle these issues, we present a nove
 l image color...\n\n\nNir Zabari, Aharon Azulay, Alexey Gorkor, and Tavi H
 alperin (Lightricks) and Ohad Fried (Reichman University)\n---------------
 ------\nReShader: View-Dependent Highlights for Single Image View-Synthesi
 s\n\nIn recent years, novel view synthesis from a single image has seen si
 gnificant progress thanks to the rapid advancements in 3D scene representa
 tion and image inpainting techniques. While the current approaches are abl
 e to synthesize geometrically consistent novel views, they often do not ha
 ndle the ...\n\n\nAvinash Paliwal and Brandon G. Nguyen (Texas A&M Univers
 ity), Andrii Tsarov (Leia Inc.), and Nima Khademi Kalantari (Texas A&M Uni
 versity)\n---------------------\nAnalysis and Synthesis of Digital Dyadic 
 Sequences\n\nWe explore the space of matrix-generated $(0, m, 2)$-nets and
  $(0, 2)$-sequences in base 2, also known as digital dyadic nets and seque
 nces.\nIn computer graphics, they are arguably leading the competition for
  use in rendering.\nWe provide a complete characterization of the design s
 pace and count the ...\n\n\nAbdalla Ahmed (King Abdullah University of Sci
 ence and Technology (KAUST)) and Mikhail Skopenkov, Markus Hadwiger, and P
 eter Wonka (KAUST)\n---------------------\nHigh Density Ratio Multi-fluid 
 Simulation with Peridynamics\n\nMultiple fluid simulation has raised wide 
 research interest in recent years. Despite the impressive successes of cur
 rent works, simulation of scenes containing mixing or unmixing of high-den
 sity-ratio phases using particle-based discretizations still remains a cha
 llenging task. In this paper, we pro...\n\n\nHan Yan and Bo Ren (Nankai Un
 iversity)\n---------------------\nTowards Practical Capture of High-Fideli
 ty Relightable Avatars\n\nIn this paper, we propose a novel framework, Tra
 cking-free Relightable Avatar (TRAvatar), for capturing and reconstructing
  high-fidelity 3D avatars. Compared to previous methods, TRAvatar works in
  a more practical and efficient setting. Specifically, TRAvatar is trained
  with dynamic image sequences ...\n\n\nHaotian Yang, Mingwu Zheng, Wanquan
  Feng, and Haibin Huang (Kuaishou Technology); Yu-Kun Lai (Cardiff Univers
 ity); and Pengfei Wan, Zhongyuan Wang, and Chongyang Ma (Kuaishou Technolo
 gy)\n---------------------\nProSpect: Prompt Spectrum for Attribute-Aware 
 Personalization of Diffusion Models\n\nPersonalizing generative models off
 ers a way to guide image generation with user-provided references. Current
  personalization methods can invert an object or concept into the textual 
 conditioning space and compose new natural sentences for text-to-image dif
 fusion models. However, representing and ed...\n\n\nYuxin Zhang (MAIS, Ins
 titute of Automation, Chinese Academy of Sciences; School of Artificial In
 telligence, University of Chinese Academy of Sciences); Weiming Dong (MAIS
 , Institute of Automation, Chinese Academy of Sciences; School of AI,Unive
 rsity of Chinese Academy of Sciences); Fan Tang (Institute of Computing Te
 chnology, Chinese Academy of Sciences); Nisha Huang (School of AI,Universi
 ty of Chinese Academy of Sciences; MAIS, Institute of Automation, Chinese 
 Academy of Sciences); Haibin Huang and Chongyang Ma (Kuaishou Technology);
  Tong-Yee Lee (National Cheng-Kung University); Oliver Deussen (University
  of Konstanz); and Changsheng Xu (MAIS, Institute of Automation, Chinese A
 cademy of Sciences; School of Artificial Intelligence, University of Chine
 se Academy of Sciences)\n---------------------\nNonlinear Ray Tracing for 
 Displacement and Shell Mapping\n\nDisplacement mapping and shell mapping a
 dd fine-scale geometric features to meshes and can significantly enhance t
 he realism of an object's surface representation. Both methods generate ge
 ometry within a layer between a base mesh and its offset mesh called a she
 ll. It is not easy to simultaneously a...\n\n\nShinji Ogaki (ZOZO, Inc.)\n
 ---------------------\nA Parametric Kinetic Solver for Simulating Boundary
 -Dominated Turbulent Flow Phenomena\n\nBoundary layer flow plays a very im
 portant role in shaping the entire flow feature near and behind obstacles 
 inside fluids. Thus, boundary treatment methods are crucial for a physical
 ly consistent fluid simulation, especially when turbulence occurs at a hig
 h Reynolds number, in which accurately hand...\n\n\nMengyun Liu and Xiaope
 i Liu (ShanghaiTech University)\n---------------------\nVMesh: Hybrid Volu
 me-Mesh Representation for Efficient View Synthesis\n\nWith the emergence 
 of neural radiance fields (NeRFs), view synthesis quality has reached an u
 nprecedented level. Compared to traditional mesh-based assets, this volume
 tric representation is more powerful in expressing scene geometry but inev
 itably suffers from high rendering costs and can hardly be ...\n\n\nYuan-C
 hen Guo (Tsinghua University, Tencent); Yan-Pei Cao (Tencent); Chen Wang (
 Tsinghua University); Yu He (Chinese Academy of Sciences); Ying Shan (Tenc
 ent); and Song-Hai Zhang (Tsinghua University)\n---------------------\nNeu
 ral Motion Graph\n\nDeep learning techniques have been employed to design 
 a controllable human motion synthesizer. Despite their potential, however,
  designing a neural network-based motion synthesis that enables flexible u
 ser interaction, fine-grained controllability, and the support of new type
 s of motions at reduced ...\n\n\nHongyu Tao, Shuaiying Hou, Changqing Zou,
  Hujun Bao, and Weiwei Xu (Zhejiang University)\n---------------------\nEn
 hancing Diffusion Models with 3D Perspective Geometry Constraints\n\nWhile
  perspective is a well-studied topic in art, it is generally taken for gra
 nted in images. However, for the recent wave of high-quality image synthes
 is methods such as latent diffusion models, perspective accuracy is not an
  explicit requirement. Since these methods are capable of outputting a wi.
 ..\n\n\nRishi Upadhyay and Howard Zhang (University of California, Los Ang
 eles); Yunhao Ba (University of California, Los Angeles; Sony); Ethan Yang
 , Blake Gella, and Sicheng Jiang (University of California, Los Angeles); 
 Alex Wong (Yale University); and Achuta Kadambi (University of California,
  Los Angeles)\n---------------------\nWarped-Area Reparameterization of Di
 fferential Path Integrals\n\nPhysics-based differentiable rendering is bec
 oming increasingly crucial for tasks in inverse rendering and machine lear
 ning pipelines. To address discontinuities caused by geometric boundaries 
 and occlusion, two classes of methods have been proposed: 1) the edge samp
 ling methods that directly sample...\n\n\nPeiyu Xu (University of Californ
 ia Irvine), Sai Bangaru (MIT CSAIL), Tzu-Mao Li (University of California 
 San Diego), and Shuang Zhao (University of California Irvine)\n-----------
 ----------\nSOL-NeRF: Sunlight Modeling for Outdoor Scene Decomposition an
 d Relighting\n\nOutdoor scenes often involve large-scale geometry and comp
 lex unknown lighting conditions, making it difficult to decompose them int
 o geometry, reflectance and illumination. Recently researchers made attemp
 ts to decompose outdoor scenes using Neural Radiance Fields (NeRF) and lea
 rning-based lighting...\n\n\nJia-Mu Sun and Tong Wu (Institute of Computin
 g Technology, Chinese Academy of Sciences; University of Chinese Academy o
 f Sciences); Yong-Liang Yang (University of Bath); Yu-Kun Lai (Cardiff Uni
 versity); and Lin Gao (Institute of Computing Technology, Chinese Academy 
 of Sciences; University of Chinese Academy of Sciences)\n-----------------
 ----\nDifferentiable Rendering of Parametric Geometry\n\nWe propose an eff
 icient method for differentiable rendering of parametric surfaces and curv
 es, which enables their use in inverse graphics problems. Our central obse
 rvation is that a representative triangle mesh can be extracted from a con
 tinuous parametric object in a differentiable and efficient w...\n\n\nMark
 us Worchel and Marc Alexa (TU Berlin)\n---------------------\nViCMA: Visua
 l Control of Multibody Animations\n\nMotion control of large-scale, multib
 ody physics animations with contact is difficult. Existing approaches, suc
 h as those based on optimization, are computationally daunting, and, as th
 e number of interacting objects increases, can fail to find satisfactory s
 olutions. We present a new, complementary...\n\n\nDoug L. James (Stanford 
 University, NVIDIA) and David I. W. Levin (University of Toronto, NVIDIA)\
 n---------------------\nOptimal Design of Robotic Character Kinematics\n\n
 The kinematic motion of a robotic character is defined by its mechanical j
 oints and actuators that restrict the relative motion of its rigid compone
 nts. Designing robots that perform a given target motion as closely as pos
 sible with a fixed number of actuated degrees of freedom is challenging, e
 spec...\n\n\nGuirec Maloisel, Christian Schumacher, Espen Knoop, Ruben Gra
 ndia, and Moritz Bächer (Disney Research)\n---------------------\nMetric O
 ptimization in Penner Coordinates\n\nMany parametrization and mapping-rela
 ted problems in geometry processing can be viewed as metric optimization p
 roblems, i.e., computing a metric minimizing a functional and satisfying a
  set of constraints, such as flatness. \n\nPenner coordinates are global c
 oordinates on the space of metrics on meshe...\n\n\nRyan Capouellez and De
 nis Zorin (New York University)\n---------------------\nThe Design Space o
 f Kirchhoff Rods\n\nThe Kirchhoff rod model describes the deformation beha
 vior of elastic rods interacting with boundary conditions. We characterize
  the set of all equilibrium states admitted by this model, assuming spatia
 lly-varying cross sections, and present an algorithm to compute the geomet
 ry of a rod that will pr...\n\n\nChristian Hafner (Institute of Science an
 d Technology Austria) and Bernd Bickel (Institute of Science and Technolog
 y Austria, Google Research)\n---------------------\nCLIPXPlore: Coupled CL
 IP and Shape Spaces for 3D Shape Exploration\n\nThis paper presents CLIPXP
 lore, a new framework that leverages a vision-language model to guide the 
 exploration of the 3D shape space. Many recent methods have been developed
  to encode 3D shapes into a learned latent shape space to enable generativ
 e design and modeling. Yet, existing methods lack ef...\n\n\nJingyu Hu, Ka
 -Hei Hui, and Zhengzhe Liu (The Chinese University of Hong Kong); Hao (Ric
 hard) Zhang (Simon Fraser University); and Chi-Wing Fu (The Chinese Univer
 sity of Hong Kong)\n---------------------\nRMIP: Displacement ray tracing 
 via inversion and oblong bounding\n\nHigh-performance ray tracing of trian
 gle meshes equipped with displacement maps is a challenging task. Existing
  methods either rely on pre-tessellation, taking full advantage of the har
 dware but with a poor memory quality tradeoff, or use custom displacement-
 centric acceleration structures, preservi...\n\n\nTheo Thonat, Iliyan Geor
 giev, François Beaune, and Tamy Boubekeur (Adobe)\n---------------------\n
 PSDR-Room: Single Photo to Scene using Differentiable Rendering\n\nA 3D di
 gital scene composes many components: lights, materials and geometries, in
 teracting to reach the desired appearance. Staging such a scene is time-co
 nsuming and requires both artistic and technical skills. In this work, we 
 propose a system allowing to optimize lighting as well as the pose and ...
 \n\n\nKai Yan (University of California, Irvine; Adobe Research); Fujun Lu
 an, Miloš Hašan, Thibault Groueix, and Valentin Deschaintre (Adobe Researc
 h); and Shuang Zhao (University of California, Irvine)\n------------------
 ---\nDiffFR: Differentiable SPH-based Fluid-Rigid Coupling for Rigid Body 
 Control\n\nDifferentiable physics simulation has shown its efficacy in inv
 erse design problems. Given the pervasiveness of the diverse interactions 
 between fluids and solids in life, a differentiable simulator for the inve
 rse design of the motion of rigid objects in two-way fluid-rigid coupling 
 is also demande...\n\n\nZhehao Li and Qingyu Xu (University of Science and
  Technology of China), Xiaohan Ye and Bo Ren (Nankai University), and Liga
 ng Liu (University of Science and Technology of China)\n------------------
 ---\nGANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields\
 n\nNeural Radiance Fields (NeRF) have shown impressive novel view synthesi
 s results; nonetheless, even thorough recordings yield imperfections in re
 constructions, for instance due to poorly observed areas or minor lighting
  changes.\nOur goal is to mitigate these imperfections from various source
 s with a...\n\n\nBarbara Roessle and Norman Müller (Technical University o
 f Munich); Lorenzo Porzi, Samuel Rota Bulò, and Peter Kontschieder (Meta R
 eality Labs); and Matthias Niessner (Technical University of Munich)\n----
 -----------------\nNeural Cache for Monte Carlo Partial Differential Equat
 ion Solver\n\nThis paper presents a method that uses neural networks as a 
 caching mechanism to reduce the variance of Monte Carlo Partial Differenti
 al Equation solvers, such as the Walk-on-Spheres algorithm. While these Mo
 nte Carlo PDE solvers have the merits of being unbiased and discretization
 -free, their high ...\n\n\nZilu Li (Cornell University); Guandao Yang (Cor
 nell University, Stanford University); and Xi Deng, Christopher De Sa, Bha
 rath Hariharan, and Steve Marschner (Cornell University)\n\nRegistration C
 ategory: Full Access, Enhanced Access, Trade Exhibitor, Experience Hall Ex
 hibitor
END:VEVENT
END:VCALENDAR