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_379@linklings.com
SUMMARY:Reconstructing Hand-Held Objects from Monocular Video
DESCRIPTION:Technical Papers\n\nReconstructing Hand-Held Objects from Mono
 cular Video\n\nHuang, Ji, He, Sun, He...\n\nThis paper presents an approac
 h that reconstructs a hand-held object from a monocular video. In contrast
  to many recent methods that directly predict object geometry by a trained
  network, the proposed approach does not require any learned prior about t
 he object and is able to recover more accurate and detailed object geometr
 y. The key idea is that the hand motion naturally provides multiple views 
 of the object and the motion can be reliably estimated by a hand pose trac
 ker. Then, the object geometry can be recovered by solving a multi-view re
 construction problem. We devise an implicit neural representation-based me
 thod to solve the reconstruction problem and address the issues of impreci
 se hand pose estimation, relative hand-object motion, and insufficient geo
 metry optimization for small objects. We also provide a newly collected da
 taset with 3D ground truth to validate the proposed approach.\n\nRegistrat
 ion Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRAD
 E EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_379&sess=sess15
 3
END:VEVENT
END:VCALENDAR