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:20240214T070248Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T163500
DTEND;TZID=Australia/Melbourne:20231214T165000
UID:siggraphasia_SIGGRAPH Asia 2023_sess166_papers_629@linklings.com
SUMMARY:From Skin to Skeleton : Towards Biomechanically Accurate 3D Digita
 l Humans
DESCRIPTION:Technical Communications, Technical Papers\n\nMarilyn Keller (
 Max Planck Institute for Intelligent Systems), Keenon Werling (Stanford Un
 iversity), Soyong Shin (Max-Planck-Institut für Informatik), Scott Delp (S
 tanford), Sergi Pujades (INRIA), Karen Liu (Stanford University), and Mich
 ael Black (Max Planck Institute for Intelligent Systems)\n\nGreat progress
  has been made in estimating 3D human pose and shape from images and video
  by training neural networks to directly regress the parameters of paramet
 ric human models like SMPL.\nHowever, existing body models have simplified
  kinematic structures that do not correspond to accurate joint locations a
 nd articulations in the human skeletal system, limiting their potential us
 e in biomechanics. On the other hand, methods for estimating biomechanical
 ly accurate skeletal motion typically rely on complex motion capture syste
 ms and expensive optimization methods.\nWhat is needed is a parametric 3D 
 human model with a biomechanically accurate skeletal structure that can be
  easily regressed from images.\nTo that end, we develop SKEL,  which re-ri
 gs the SMPL body model with a biomechanics skeleton. To enable this, we ne
 ed training data of skeletons inside SMPL meshes in diverse poses. We buil
 d such a dataset by optimizing biomechanically accurate skeletons inside S
 MPL meshes from AMASS sequences. We then learn a regressor from SMPL mesh 
 vertices to the true joint locations and bone rotations. Finally, we re-pa
 rametrize the SMPL mesh with the new kinematic parameters.\nThe resulting 
 SKEL model is animatable like SMPL but with fewer, and biomechanically-rea
 listic, degrees of freedom. We also train a regressor from SMPL meshes to 
 the skeleton enabling us to ``upgrade" existing datasets that are in SMPL 
 format. We show that SKEL has more biomechanically accurate joint location
 s than SMPL, and the bones fit inside the body surface better than previou
 s methods.\nSKEL provides a new tool to enable biomechanics in the wild, w
 hile also providing vision and graphics researchers with a better constrai
 ned and more realistic model of human articulation.\n\nRegistration Catego
 ry: Full Access\n\nSession Chair: Seungbae Bang (Amazon, University of Tor
 onto)
URL:https://asia.siggraph.org/2023/full-program?id=papers_629&sess=sess166
END:VEVENT
END:VCALENDAR