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:20260114T163644Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T131500
DTEND;TZID=Australia/Melbourne:20231215T132500
UID:siggraphasia_SIGGRAPH Asia 2023_sess137_papers_327@linklings.com
SUMMARY:An Implicit Physical Face Model Driven by Expression and Style
DESCRIPTION:Lingchen Yang (ETH Zürich); Gaspard Zoss and Prashanth Chandra
 n (The Walt Disney Company (Switzerland) GmbH); Paulo Gotardo (Disney Rese
 arch Studios, The Walt Disney Company (Switzerland) GmbH); Markus Gross (E
 TH Zürich, The Walt Disney Company (Switzerland) GmbH); Barbara Solenthale
 r (ETH Zürich); Eftychios Sifakis (University of Wisconsin Madison); and D
 erek Bradley (The Walt Disney Company (Switzerland) GmbH)\n\n3D facial ani
 mation is often produced by manipulating facial deformation models (or rig
 s), that are traditionally parameterized by expression controls. A key com
 ponent that is usually overlooked is expression ``style", as in, how a par
 ticular expression is performed. Although it is common to define a semanti
 c basis of expressions that characters can perform, most characters perfor
 m each expression in their own style. To date, style is usually entangled 
 with the expression, and it is not possible to transfer the style of one c
 haracter to another when considering facial animation. We present a new fa
 ce model, based on a data-driven implicit neural physics model, that can b
 e driven by both expression and style separately. At the core, we present 
 a framework for learning implicit physics-based actuations for multiple su
 bjects simultaneously, trained on a few arbitrary performance capture sequ
 ences from a small set of identities. Once trained, our method allows gene
 ralized physics-based facial animation for any of the trained identities, 
 extending to unseen performances. Furthermore, it grants control over the 
 animation style, enabling style transfer from one character to another or 
 blending styles of different characters. Lastly, as a physics-based model,
  it is capable of synthesizing physical effects, such as collision handlin
 g, setting our method apart from conventional approaches.\n\nRegistration 
 Category: Full Access\n\nSession Chair: Weidan Xiong (Shenzhen University,
  College of Computer Science and Software Engineering)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_327&sess=sess137
END:VEVENT
END:VCALENDAR