BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171534Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241205T150800
DTEND;TZID=Asia/Tokyo:20241205T151900
UID:siggraphasia_SIGGRAPH Asia 2024_sess135_papers_590@linklings.com
SUMMARY:SKEL-Betweener: a Neural Motion Rig for Interactive Motion Authori
 ng
DESCRIPTION:Dhruv Agrawal (ETH Zürich, DisneyResearch|Studios) and Jakob B
 uhmann, Dominik Borer, Robert W. Sumner, and Martin Guay (DisneyResearch|S
 tudios)\n\nAuthoring 3D motions is a laborious process that requires manip
 ulating and coordinating many control handles over time. Neural motion rep
 resentations learned from large motion datasets have recently shown impres
 sive capabilities in many motion completion tasks. However, current method
 s are not designed for interactive motion authoring workflows. The reasons
  being their requirement of a dense context of full poses, which takes con
 siderable time to author, as well as their lack of joint-level controls fo
 r refinement. In this paper, we introduce a Neural Motion Rig called SKEL-
 Betweener, tailored to interactive motion authoring. SKEL-Betweener is abl
 e to generate long motion sequences from two poses only, and enables inter
 mediate motion authoring via neural motion curves—intuitive joint-level co
 ntrols for positions and orientations. Through user evaluations, we demons
 trate the effectiveness of our Neural Motion Rig for efficiently creating 
 and editing motions.\n\nRegistration Category: Full Access, Full Access Su
 pporter\n\nLanguage Format: English Language\n\nSession Chair: Changjian L
 i (University of Edinburgh)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_590&sess=sess135
END:VEVENT
END:VCALENDAR