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:20240214T070241Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_998@linklings.com
SUMMARY:MOCHA: Real-Time Motion Characterization via Context Matching
DESCRIPTION:Technical Papers\n\nDeok-Kyeong Jang (KAIST, MOVIN Inc.); Yuti
 ng Ye (Meta); Jungdam Won (Seoul National University); and Sung-Hee Lee (K
 AIST)\n\nTransforming neutral, characterless input motions to embody the d
 istinct style of a notable character in real time is highly compelling for
  character animation. This paper introduces MOCHA, a novel online motion c
 haracterization framework that transfers both motion styles and body propo
 rtions from a target character to an input source motion. MOCHA begins by 
 encoding the input motion into a motion feature that structures the body p
 art topology and captures motion dependencies for effective characterizati
 on. Central to our framework is the Neural Context Matcher, which generate
 s a motion feature for the target character with the most similar context 
 to the input motion feature. The conditioned autoregressive model of the N
 eural Context Matcher can produce temporally coherent character features i
 n each time frame. To generate the final characterized pose, our Character
 izer network incorporates the characteristic aspects of the target motion 
 feature into the input motion feature while preserving its context. This i
 s achieved through a transformer model that introduces the adaptive instan
 ce normalization and context mapping-based cross-attention, effectively in
 jecting the character feature into the source feature. We validate the per
 formance of our framework through comparisons with prior work and an ablat
 ion study. Our framework can easily accommodate various applications, incl
 uding characterization with only sparse input and real-time characterizati
 on. Additionally, we contribute a high-quality motion dataset comprising s
 ix different characters performing a range of motions, which can serve as 
 a valuable resource for future research.\n\nRegistration Category: Full Ac
 cess, Enhanced Access, Trade Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_998&sess=sess209
END:VEVENT
END:VCALENDAR