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_712@linklings.com
SUMMARY:Pose and Skeleton-aware Neural IK for Pose and Motion Editing
DESCRIPTION:Technical Papers\n\nDhruv Agrawal (ETH Zürich, DisneyResearch|
 Studios); Martin Guay, Jakob Buhmann, and Dominik Borer (DisneyResearch|St
 udios); and Robert W. Sumner (DisneyResearch|Studios, ETH Zürich)\n\nPosin
 g a 3D character for film or game is an iterative and laborious process wh
 ere many control handles (e.g. joints) need to be manipulated to achieve a
  compelling result.  Neural Inverse Kinematics (IK) is a new type of IK th
 at enables sparse control over a 3D character pose, and leverages full bod
 y correlations to complete the un-manipulated joints of the body.  While n
 eural IK is promising, current methods are not designed to preserve previo
 us edits in posing workflows. Current models generate a full pose from the
  handles only---regardless of what was there previously---making it diffic
 ult to preserve any variations and hindering tasks such as pose and motion
  editing.\n\nIn this paper, we introduce SKEL-IK, a novel architecture and
  training scheme that is conditioned on a base pose, and designed to flow 
 information directly onto the skeletal graph structure, such that hard con
 straints can be enforced by blocking information flows at certain joints. 
 As a result, we are able to satisfy both hard and soft constraints, as wel
 l as preserve un-manipulated parts of the body when desired. Finally, by c
 ontrolling the base pose in different ways, we demonstrate the ability of 
 our model to perform tasks such as generating variations and quickly editi
 ng poses and motions; with less erosion of the base poses compared to the 
 current state-of-the-art.\n\nRegistration Category: Full Access, Enhanced 
 Access, Trade Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_712&sess=sess209
END:VEVENT
END:VCALENDAR