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_431@linklings.com
SUMMARY:QuestSim: Human Motion Tracking from Sparse Sensors with Simulated
  Avatars
DESCRIPTION:Technical Papers\n\nQuestSim: Human Motion Tracking from Spars
 e Sensors with Simulated Avatars\n\nWinkler, Won, Ye\n\nReal-time tracking
  of human body motion is crucial for interactive and\nimmersive experience
 s in AR/VR. However, very limited sensor data about\nthe body is available
  from standalone wearable devices such as HMDs (Head\nMounted Devices) or 
 AR glasses. In this work, we present a reinforcement\nlearning framework t
 hat takes in sparse signals from an HMD and two\ncontrollers, and simulate
 s plausible and physically valid full body motions.\nUsing high quality fu
 ll body motion as dense supervision during training,\na simple policy netw
 ork can learn to output appropriate torques for the\ncharacter to balance,
  walk, and jog, while closely following the input signals.\nOur results de
 monstrate surprisingly similar leg motions to ground truth\nwithout any ob
 servations of the lower body, even when the input is only\nthe 6D transfor
 mations of the HMD. We also show that a single policy\ncan be robust to di
 verse locomotion styles, different body sizes, and novel\nenvironments.\n\
 nRegistration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE AC
 CESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_431&sess=sess15
 3
END:VEVENT
END:VCALENDAR