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:20260114T163652Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T104000
DTEND;TZID=Australia/Melbourne:20231214T105500
UID:siggraphasia_SIGGRAPH Asia 2023_sess129_papers_371@linklings.com
SUMMARY:DR-Occluder: Generating Occluders using Differentiable Rendering
DESCRIPTION:Jiaxian Wu, Yue Lin, and Dehui Lu (NetEase Games AI Lab)\n\nTh
 e target of the occluder is to use very few faces to maintain similar occl
 usion properties of the original 3D model.\nIn this paper, we present DR-O
 ccluder, a novel coarse-to-fine framework for occluder generation that lev
 erages differentiable rendering to optimize a triangle set to an occluder.
  Unlike prior work, which has not utilized differentiable rendering for th
 is task, our approach provides the ability to optimize a 3D shape to defin
 ed targets. Given a 3D model as input, our method first projects it to sil
 houette images, which are then processed by a convolution network to outpu
 t a group of vertex offsets. These offsets are used to transform a group o
 f distributed triangles into a preliminary occluder, which is further opti
 mized by differentiable rendering. Finally, triangles whose area is smalle
 r than a threshold are removed to obtain the final occluder. Our extensive
  experiments demonstrate that DR-Occluder significantly outperforms state-
 of-the-art methods in terms of occlusion quality. Furthermore, we compare 
 the performance of our method with other approaches in a commercial engine
 , providing compelling evidence of its effectiveness.\n\nRegistration Cate
 gory: Full Access\n\nSession Chair: Marc Stamminger (Friedrich-Alexander-U
 niversität Erlangen-Nürnberg (FAU))\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_371&sess=sess129
END:VEVENT
END:VCALENDAR