BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070245Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T175500
DTEND;TZID=Australia/Melbourne:20231213T180500
UID:siggraphasia_SIGGRAPH Asia 2023_sess167_papers_1057@linklings.com
SUMMARY:ACE: Adversarial Correspondence Embedding for Cross Morphology Mot
 ion Retargeting from Human to Nonhuman Characters
DESCRIPTION:Technical Communications, Technical Papers\n\nTianyu Li (Georg
 ia Institute of Technology), Jungdam Won (Seoul National University), Alex
 ander Clegg (Meta), Jeonghwan Kim (Georgia Institute of Technology), Aksha
 ra Rai (Meta), and Sehoon Ha (Georgia Institute of Technology)\n\nMotion r
 etargeting is a promising approach for generating natural and compelling m
 otions for nonhuman characters. However, it is challenging to translate hu
 man movements into semantically equivalent motions for target characters w
 ith very different morphologies due to ambiguity. This work presents a nov
 el learning-based motion retargeting framework, Adversarial Correspondence
  Embedding (ACE), to retarget human motions onto target characters with di
 fferent body dimensions and structures. Our framework is designed to produ
 ce natural and feasible robot motions by leveraging generative-adversarial
  networks (GANs) while preserving high-level motion semantics by introduci
 ng an additional feature loss. In addition, we pretrain a robot motion pri
 or that can be controlled in a latent embedding space and seek to establis
 h a compact correspondence. We demonstrate that the proposed framework can
  produce convincing retargeted motions for three different characters, a q
 uadrupedal robot with a manipulator, a crab character, and a wheeled manip
 ulator. We further validate the design choices of our framework by conduct
 ing baseline comparisons and user studies. We also demonstrate the sim-to-
 real of the retargeted motions by transferring it to the real Spot robot.\
 n\nRegistration Category: Full Access\n\nSession Chair: Yoonsang Lee (Hany
 ang University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_1057&sess=sess16
 7
END:VEVENT
END:VCALENDAR