BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260805T205518Z
LOCATION:Room 403 A
DTSTART;TZID=America/Los_Angeles:20260722T090000
DTEND;TZID=America/Los_Angeles:20260722T103000
UID:siggraph_SIGGRAPH 2026_sess114@linklings.com
SUMMARY:Motion Transfer & Inbetweening
DESCRIPTION:Motion4Motion: Motion Transfer Across Subjects at Inference\n\
 nThis work proposes a novel framework, Motion4Motion, for transferring a m
 otion from one subject to another in a video. Without a skeleton or neural
  network training, Motion4Motion runs efficiently at inference.\n\n\nLing-
 Hao Chen (Tsinghua University, Stepfun); Zixin Yin (Hong Kong University o
 f Science and Technology, Stepfun); and Duomin Wang, Xianfang Zeng, and Ga
 ng Yu (Stepfun)\n---------------------\nSTyMo: Fast and Controllable Few-S
 hot Motion Style Transfer\n\nSTyMo is a few-shot approach that learns moti
 on style from only seconds of paired data and trains in one to two minutes
 . Our key insight is to decompose style into two components: a static comp
 onent capturing time-invariant posture, and a temporal component capturing
  frame-wise dynamics.\n\n\nJose Luis Ponton (Reality Labs, Meta; Universit
 at Politècnica de Catalunya (UPC)) and Alexander Winkler, Ladislav Kavan, 
 Yuting Ye, and Petr Kadlecek (Reality Labs, Meta)\n---------------------\n
 Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance\n\
 nWe present a geometry-aware motion retargeting framework that preserves i
 nteraction semantics by performing proximity matching over spatially adapt
 ive anchors. Unlike prior methods with static anchor definitions, our meth
 od dynamically repositions anchors to reachable regions on the target char
 acter...\n\n\nSoojin Choi, Seokhyeon Hong, Chaelin Kim, Junghyun Nam, Junh
 yuk Jeon, and Junyong Noh (Korea Advanced Institute of Science and Technol
 ogy (KAIST))\n---------------------\nReActor: Reinforcement Learning for P
 hysics-Aware Motion Retargeting\n\nWe present a reinforcement learning-bas
 ed retargeting method that transfers human motion to diverse morphologies,
  including humanoids and a quadruped, without artifacts such as foot-slidi
 ng, hovering, or self-penetration. A bilevel optimization framework refine
 s upper-loop retargeting parameters def...\n\n\nDavid Müller, Agon Serifi,
  Sammy Christen, Ruben Grandia, Espen Knoop, and Moritz Bächer (Disney Res
 earch)\n---------------------\nAdaptive Interpolation-Synthesis for Motion
  In-Betweening on Keyframe-Based Animation\n\nWe propose a motion in-betwe
 ening method tailored to stylized keyframe-based animation production. Our
  Adaptive Interpolation–Synthesis layer dynamically blends learned interpo
 lation with direct pose synthesis, mirroring the animator's workflow. Comb
 ined with a domain-based input keypose train...\n\n\nAnton Raël, Julien Bo
 ucher, and Antoine Lhermitte (Animaj)\n---------------------\nLayerInbetwe
 en: Occlusion-Aware Stroke Correspondence and Inbetweening with Automatic 
 Layering\n\nLayerInbetween is an occlusion-aware framework for vector stro
 ke correspondence and automatic inbetweening. It performs automatic layeri
 ng to guide stroke tracing and correspondence finding for occluded strokes
 , and to resolve occlusion with layers in the inbetween frames. The vector
 -based method en...\n\n\nHaoran Mo (The Hong Kong University of Science an
 d Technology (Guangzhou)); Zhongyue Guan (The Hong Kong University of Scie
 nce and Technology (Guangzhou), Tencent); Yixin Hu (Tencent America); and 
 Zeyu Wang (The Hong Kong University of Science and Technology (Guangzhou),
  The Hong Kong University of Science and Technology)\n--------------------
 -\nMotion Transfer & Inbetweening - Interactive Discussion\n\nAfter the su
 mmary presentations, attendees will participate in an interactive discussi
 on. Outside the room will be a series of poster boards for authors to gath
 er around with the audience. Authors are invited to bring any material rel
 ated to their paper that could instigate further conversation such...\n\n\
 nInterest Area: Research & Education\n\nKeyword: Animation, Artificial Int
 elligence/Machine Learning, Robotics, Simulation\n\nRegistration Category:
  Full Conference Supporter, Full Conference\n\nSession Chair: Pei Xu (Stan
 ford University)
END:VEVENT
END:VCALENDAR