BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212948Z
LOCATION:Mile High 1
DTSTART;TZID=America/Denver:20240730T140000
DTEND;TZID=America/Denver:20240730T153000
UID:siggraph_SIGGRAPH 2024_sess115@linklings.com
SUMMARY:3D People and Their Habitats
DESCRIPTION:Compressed Skinning for Facial Blendshapes\n\nWe present a new
  skinning decomposition method and its application to facial animation, sp
 ecifically blendshape compression. Our new algorithm based on Adam with pr
 ojection outperforms SOTA (Dem Bones) and even allows us to sparsify the b
 one-bone transformations for further compression.\n\n\nLadislav Kavan, Joh
 n Doublestein, Martin Prazak, Matthew Cioffi, and Doug Roble (Meta)\n-----
 ----------------\nHAISOR: Human-Aware Indoor Scene Optimization via Deep R
 einforcement Learning\n\nHAISOR proposes a pipeline to use deep reinforcem
 ent learning and Monte Carlo tree search to solve indoor scene optimizatio
 n problem incorporating human behavior including human-furniture interacti
 on and free space of activities that is not differentiable.\n\n\nJia-Mu Su
 n (Insititute of Computing Technology Chinese Academy of Sciences, Univers
 ity of Chinese Academy of Sciences); Jie Yang (Chinese Academy of Sciences
  Institute of Computing Technology); Kaichun Mo (NVIDIA Research); Yukun L
 ai (Cardiff University); Leonidas Guibas (Stanford University); Lin Gao (U
 niversity of the Chinese Academy of Sciences); and Jia-Mu Sun\n-----------
 ----------\nSpatial and Surface Correspondence Field for Interaction Trans
 fer\n\nWe introduce a new method for the task of interaction transfer. Giv
 en an example interaction between a source object and an agent, our method
  can automatically infer both surface and spatial relationships for the ag
 ent and target objects within the same category, yielding more accurate an
 d valid tra...\n\n\nZeyu Huang and Honghao Xu (Shenzhen University), Haibi
 n Huang and Chongyang Ma (Kuaishou Technology), and Hui Huang and Ruizhen 
 Hu (Shenzhen University)\n---------------------\nPhysics-based Scene Layou
 t Generation From Human Motion\n\nWe present a physics-based framework tha
 t generates scene layouts from captured human motions. By simultaneously o
 ptimizing the motion imitation character controller and the scene layout g
 enerator, our method generates physically plausible and semantically reaso
 nable scenes for a range of motions.\n\n\nJianan Li and Tao Huang (The Chi
 nese University of Hong Kong), Qingxu Zhu (Tencent Robotics X), and Tien-T
 sin Wong (The Chinese University of Hong Kong)\n---------------------\n3D 
 People and Their Habitats - Interactive Discussion\n\nAfter the summary pr
 esentations, attendees will participate in an interactive discussion. Dist
 ributed around the room will be a series of poster boards for authors to g
 ather around with the audience. Authors are invited to bring any material 
 related to their paper that could instigate further conver...\n\n---------
 ------------\nVRMM: A Volumetric Relightable Morphable Head Model\n\nWe pr
 esent the Volumetric Relightable Morphable Model (VRMM), a novel volumetri
 c and parametric facial prior. Our VRMM utilizes a novel training framewor
 k to efficiently disentangle and encode identity, expression, and lighting
  into low-dimensional representations. It facilitates the reconstruction .
 ..\n\n\nHaotian Yang, Mingwu Zheng, and Chongyang Ma (Kuaishou Technology)
 ; Yu-Kun Lai (Cardiff University); and Pengfei Wan and Haibin Huang (Kuais
 hou Technology)\n---------------------\nCharacterGen: Efficient 3D Charact
 er Generation From Single Images With Multi-view Pose Canonicalization\n\n
 CharacterGen introduces a streamlined 3D character generation pipeline, wh
 ich can generate high-quality canonicalized characters from given images w
 ithin one minute. Additionally, we have curated a dataset, Anime3D, which 
 renders anime characters in multiple poses and views to train and evaluate
  our...\n\n\nHao-Yang Peng, Jia-Peng Zhang, and Meng-Hao Guo (Tsinghua Uni
 versity); Yan-Pei Cao (VAST); and Shi-Min Hu (Tsinghua University)\n\nInte
 rest Area: Research & Education\n\nKeyword: Animation, Geometry, Machine L
 earning, Modeling\n\nRegistration Category: Full Conference, Full Conferen
 ce Supporter, Virtual Access, Exhibitor Full Conference, Tuesday\n\nSessio
 n Chair: Stephen Lombardi (Google)
END:VEVENT
END:VCALENDAR