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:20260817T171534Z
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:Inseo Jang, Soojin Choi, Seokhyeon Hong, Chaelin Kim, and Juny
 ong Noh (Korea Advanced Institute of Science and Technology (KAIST))\n\nIn
 teractive motion between multiple characters is widely utilized in games a
 nd movies. However, the method for transitioning interactive motions consi
 dering the character's diverse mesh shape has yet to be studied. We propos
 e a Spatio Cooperative Transformer (SCT) to retarget the interacting motio
 ns of two characters having arbitrary mesh topologies. SCT predicts residu
 al of root position and joint rotations considering the shape difference b
 etween the source and target of interacting characters. In addition, we in
 troduce an anchor loss function for SCT to maintain geometric distance bet
 ween interacting characters from source to target characters. We also prop
 ose a motion augmentation method with deformation-based adaptation to prep
 are a source-target paired dataset with identical mesh topologies. In expe
 riments, our method shows higher accuracy for semantic preservation and lo
 wer artifacts of inter-penetration between interacting characters for the 
 unseen character and motion than the baselines. Moreover, we conduct a use
 r evaluation across various shapes of characters, spanning low-to-high int
 eraction levels to show better semantic preservation of our method compare
 d to previous works.\n\nRegistration Category: Full Access, Full Access Su
 pporter\n\nLanguage Format: English Language\n\nSession Chair: Jungdam Won
  (Seoul National University)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_778&sess=sess117
END:VEVENT
END:VCALENDAR