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_170@linklings.com
SUMMARY:UmeTrack: Unified multi-view end-to-end hand tracking for VR
DESCRIPTION:Technical Papers\n\nUmeTrack: Unified multi-view end-to-end ha
 nd tracking for VR\n\nHan, Wu, Zhang, Liu, Zhang...\n\nReal-time tracking 
 of 3D hand pose in world space is a challenging problem\nand plays an impo
 rtant role in VR interaction. Existing work in this space are\nlimited to 
 either producing root-relative (versus world space) 3D pose or rely\non mu
 ltiple stages such as generating heatmaps and kinematic optimization\nto o
 btain 3D pose. Moreover, the typical VR scenario, which involves multiview
 \ntracking from wide field of view (FOV) cameras is seldom addressed by\nt
 hese methods. In this paper, we present a unified end-to-end differentiabl
 e\nframework for multi-view, multi-frame hand tracking that directly predi
 cts\n3D hand pose in world space. We demonstrate the benefits of end-to-en
 d\ndifferentiabilty by extending our framework with downstream tasks such\
 nas jitter reduction and pinch prediction. To demonstrate the efficacy of 
 our\nmodel,we further present a newlarge-scale egocentric hand pose datase
 t that\nconsists of both real and synthetic data. Experiments show that ou
 r system\nhandles various challenging interactive motions, and has been su
 ccessfully\napplied to real-time VR applications.\n\nRegistration Category
 : FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\
 n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_170&sess=sess15
 3
END:VEVENT
END:VCALENDAR