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_366@linklings.com
SUMMARY:Learning Virtual Chimeras by Dynamic Motion Reassembly
DESCRIPTION:Technical Papers\n\nLearning Virtual Chimeras by Dynamic Motio
 n Reassembly\n\nLEE, Lee, Lee\n\nThe Chimera is a mythological hybrid crea
 ture composed of different animal parts. The chimera’s movements are highl
 y dependent on the spatial and temporal alignments of its composing parts.
  In this paper, we present a novel algorithm that creates and animates chi
 meras by dynamically reassembling source characters and their movements. O
 ur algorithm exploits a two-network architecture: part assembler and dynam
 ic controller. The part assembler is a supervised learning layer that sear
 ches for the spatial alignment among body parts, assuming that the tempora
 l alignment is provided. The dynamic controller is a reinforcement learnin
 g layer that learns robust control policy for a wide variety of potential 
 temporal alignments. These two layers are tightly intertwined and learned 
 simultaneously. The chimera animation generated by our algorithm is energy
  efficient and expressive in terms of describing weight shifting, balancin
 g, and full-body coordination. We demonstrate the versatility of our algor
 ithm by generating the motor skills of a large variety of chimeras from li
 mited source characters.\n\nRegistration Category: FULL ACCESS, EXPERIENCE
  PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nF
 ormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_366&sess=sess15
 3
END:VEVENT
END:VCALENDAR