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_204@linklings.com
SUMMARY:Pattern-Based Cloth Registration and Sparse-View Animation
DESCRIPTION:Technical Papers\n\nPattern-Based Cloth Registration and Spars
 e-View Animation\n\nHalimi, Stuyck, Xiang, Bagautdinov, Wen...\n\nWe propo
 se a novel multi-view camera pipeline for the reconstruction and registrat
 ion of dynamic clothing.\nOur proposed method relies on a specifically des
 igned pattern that allows for precise video tracking in each camera view. 
 \nWe triangulate the tracked points and register the cloth surface in a fi
 ne-grained geometric resolution and low localization error. \nCompared to 
 state-of-the-art methods, our registration exhibits stable correspondence,
  tracking the same points on the deforming cloth surface along the tempora
 l sequence.\nAs an application, we demonstrate how the use of our registra
 tion pipeline greatly improves state-of-the-art pose-based drivable cloth 
 models.\nFurthermore, we propose a novel model, Garment Avatar, for drivin
 g cloth from a dense tracking signal which is obtained from two opposing c
 amera views. The method produces realistic reconstructions which are faith
 ful to the actual geometry of the deforming cloth. \nIn this setting, the 
 user wears a garment with our custom pattern which enables our driving mod
 el to reconstruct the geometry. We will release our pattern and registered
  mesh sequences containing 4 different subjects, and 15k frames in total.\
 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_204&sess=sess15
 3
END:VEVENT
END:VCALENDAR