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:20260114T163652Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T091000
DTEND;TZID=Australia/Melbourne:20231215T092500
UID:siggraphasia_SIGGRAPH Asia 2023_sess134_papers_937@linklings.com
SUMMARY:Variational Barycentric Coordinates
DESCRIPTION:Ana Dodik (MIT CSAIL); Oded Stein (University of Southern Cali
 fornia, MIT CSAIL); and Vincent SItzmann and Justin Solomon (MIT CSAIL)\n\
 nWe propose a variational technique to optimize for generalized barycentri
 c coordinates that offers additional artistic control compared to existing
  models. Prior work represents barycentric coordinates using meshes or clo
 sed-form formulae, in practice limiting the choice of objective function. 
 In contrast, we directly parameterize the continuous function that maps an
 y coordinate in a polytope's interior to its barycentric coordinates using
  a neural field. This formulation is enabled by our theoretical characteri
 zation of barycentric coordinates, which allows us to construct neural fie
 lds that parameterize the entire function class of valid coordinates. We d
 emonstrate the flexibility of our model using a variety of objective funct
 ions, including multiple smoothness and deformation-aware energies; as a s
 ide contribution, we also present mathematically-justified means of measur
 ing and minimizing objectives like total variation on discontinuous neural
  fields. We offer a practical acceleration strategy, present a thorough va
 lidation of our algorithm, and demonstrate several applications.\n\nRegist
 ration Category: Full Access\n\nSession Chair: Juno Kim (University of New
  South Wales; School of Optometry and Vision Science, Faculty of Medicine 
 and Health, UNSW)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_937&sess=sess134
END:VEVENT
END:VCALENDAR