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:20260114T163649Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T115000
DTEND;TZID=Australia/Melbourne:20231214T120000
UID:siggraphasia_SIGGRAPH Asia 2023_sess150_papers_535@linklings.com
SUMMARY:Explorable Mesh Deformation Subspaces from Unstructured 3D Generat
 ive Models
DESCRIPTION:Arman Maesumi (Brown University); Paul Guerrero, Vladimir Kim,
  and Matthew Fisher (Adobe Inc.); Siddhartha Chaudhuri (Adobe Inc.; Indian
  Institute of Technology (IIT), Bombay); Noam Aigerman (Adobe Inc.); and D
 aniel Ritchie (Brown University)\n\nExploring variations of 3D shapes is a
  time-consuming process in traditional 3D modeling tools. Deep generative 
 models of 3D shapes often feature continuous latent spaces that can, in pr
 inciple, be used to explore potential variations starting from a set of in
 put shapes; in practice, doing so can be problematic---latent spaces are h
 igh dimensional and hard to visualize, contain shapes that are not relevan
 t to the input shapes, and linear paths through them often lead to sub-opt
 imal shape transitions. Furthermore, one would ideally be able to explore 
 variations in the original high-quality meshes used to train the generativ
 e model, not its lower-quality output geometry. In this paper, we present 
 a method to explore variations among a given set of landmark shapes by con
 structing a mapping from an easily-navigable 2d exploration space to a sub
 space of a pre-trained generative model. We first describe how to find a m
 apping that spans the set of input landmark shapes and exhibits smooth var
 iations between them. We then show how to turn the variations in this subs
 pace into deformation fields, to transfer those variations to high-quality
  meshes for the landmark shapes. Our results show that our method can prod
 uce visually-pleasing and easily-navigable 2D exploration spaces for sever
 al different shape categories, especially as compared to prior work on lea
 rning deformation spaces for 3D shapes.\n\nRegistration Category: Full Acc
 ess\n\nSession Chair: Peng-Shuai Wang (Peking University)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_535&sess=sess150
END:VEVENT
END:VCALENDAR