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:20240214T070247Z
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:Technical Papers\n\nJiaxian Wu, Yue Lin, and Dehui Lu (NetEase
  Games AI Lab)\n\nThe target of the occluder is to use very few faces to m
 aintain similar occlusion properties of the original 3D model.\nIn this pa
 per, 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. Unlike prior work, which has not utilized differentia
 ble rendering for this task, our approach provides the ability to optimize
  a 3D shape to defined targets. Given a 3D model as input, our method firs
 t projects it to silhouette images, which are then processed by a convolut
 ion network to output a group of vertex offsets. These offsets are used to
  transform a group of distributed triangles into a preliminary occluder, w
 hich is further optimized by differentiable rendering. Finally, triangles 
 whose area is smaller than a threshold are removed to obtain the final occ
 luder. Our extensive experiments demonstrate that DR-Occluder significantl
 y outperforms state-of-the-art methods in terms of occlusion quality. Furt
 hermore, we compare the performance of our method with other approaches in
  a commercial engine, providing compelling evidence of its effectiveness.\
 n\nRegistration Category: Full Access\n\nSession Chair: Marc Stamminger (F
 riedrich-Alexander-Universität Erlangen-Nürnberg)
URL:https://asia.siggraph.org/2023/full-program?id=papers_371&sess=sess129
END:VEVENT
END:VCALENDAR