BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_584@linklings.com
SUMMARY:Scene Synthesis from Human Motion
DESCRIPTION:Technical Papers\n\nScene Synthesis from Human Motion\n\nYe, W
 ang, Li, Park, Liu...\n\nLarge-scale capture of human motion with diverse,
  complex scenes, while immensely useful, is often considered prohibitively
  costly. Meanwhile, human motion alone contains rich information about the
  scene they reside in and interact with. For example, a sitting human sugg
 ests the existence of a chair, and their leg position further implies the 
 chair’s pose. In this paper, we propose to synthesize diverse, semanticall
 y reasonable, and physically plausible scenes based on human motion. Our f
 ramework, Scene Synthesis from HUMan MotiON (SUMMON), includes two steps. 
 It first uses ContactFormer, our newly introduced contact predictor, to ob
 tain temporally consistent contact labels from human motion. Based on thes
 e predictions, SUMMON then chooses interacting objects and optimizes physi
 cal plausibility losses; it further populates the scene with objects that 
 do not interact with humans. Experimental results demonstrate that SUMMON 
 synthesizes feasible, plausible, and diverse scenes and has the potential 
 to generate extensive human-scene interaction data for the community.\n\nR
 egistration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCE
 SS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_584&sess=sess15
 3
END:VEVENT
END:VCALENDAR