BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241204T132300
DTEND;TZID=Asia/Tokyo:20241204T133400
UID:siggraphasia_SIGGRAPH Asia 2024_sess117_papers_778@linklings.com
SUMMARY:Geometry-Aware Retargeting for Two-Skinned Characters Interaction
DESCRIPTION:Technical Papers\n\nInseo Jang, Soojin Choi, Seokhyeon Hong, C
 haelin Kim, and Junyong Noh (Korea Advanced Institute of Science and Techn
 ology (KAIST))\n\nInteractive motion between multiple characters is widely
  utilized in games and movies. However, the method for transitioning inter
 active motions considering the character's diverse mesh shape has yet to b
 e studied. We propose a Spatio Cooperative Transformer (SCT) to retarget t
 he interacting motions of two characters having arbitrary mesh topologies.
  SCT predicts residual of root position and joint rotations considering th
 e shape difference between the source and target of interacting characters
 . In addition, we introduce an anchor loss function for SCT to maintain ge
 ometric distance between interacting characters from source to target char
 acters. We also propose a motion augmentation method with deformation-base
 d adaptation to prepare a source-target paired dataset with identical mesh
  topologies. In experiments, our method shows higher accuracy for semantic
  preservation and lower artifacts of inter-penetration between interacting
  characters for the unseen character and motion than the baselines. Moreov
 er, we conduct a user evaluation across various shapes of characters, span
 ning low-to-high interaction levels to show better semantic preservation o
 f our method compared to previous works.\n\nRegistration Category: Full Ac
 cess, Full Access Supporter\n\nLanguage Format: English Language\n\nSessio
 n Chair: Jungdam Won (Seoul National University)
URL:https://asia.siggraph.org/2024/program/?id=papers_778&sess=sess117
END:VEVENT
END:VCALENDAR