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:20240214T070250Z
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:Technical Communications, Technical Papers\n\nLingchen Yang (E
 TH Zürich); Gaspard Zoss and Prashanth Chandran (The Walt Disney Company (
 Switzerland) GmbH); Paulo Gotardo (Disney Research Studios, The Walt Disne
 y Company (Switzerland) GmbH); Markus Gross (ETH Zürich, The Walt Disney C
 ompany (Switzerland) GmbH); Barbara Solenthaler (ETH Zürich); Eftychios Si
 fakis (University of Wisconsin Madison); and Derek Bradley (The Walt Disne
 y Company (Switzerland) GmbH)\n\n3D facial animation is often produced by 
 manipulating facial deformation models (or rigs), that are traditionally p
 arameterized by expression controls. A key component that is usually overl
 ooked is expression ``style", as in, how a particular expression is perfor
 med. Although it is common to define a semantic basis of expressions that 
 characters can perform, most characters perform each expression in their o
 wn style. To date, style is usually entangled with the expression, and it 
 is not possible to transfer the style of one character to another when con
 sidering facial animation. We present a new face model, based on a data-dr
 iven implicit neural physics model, that can be driven by both expression 
 and style separately. At the core, we present a framework for learning imp
 licit physics-based actuations for multiple subjects simultaneously, train
 ed on a few arbitrary performance capture sequences from a small set of id
 entities. Once trained, our method allows generalized physics-based facial
  animation for any of the trained identities, extending to unseen performa
 nces. Furthermore, it grants control over the animation style, enabling st
 yle transfer from one character to another or blending styles of different
  characters. Lastly, as a physics-based model, it is capable of synthesizi
 ng physical effects, such as collision handling, setting our method apart 
 from conventional approaches.\n\nRegistration Category: Full Access\n\nSes
 sion Chair: Weidan Xiong (Shenzhen University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_327&sess=sess137
END:VEVENT
END:VCALENDAR