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:20250110T023312Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T165300
DTEND;TZID=Asia/Tokyo:20241205T170500
UID:siggraphasia_SIGGRAPH Asia 2024_sess136_tog_103@linklings.com
SUMMARY:TriHuman: A Real-time and Controllable Tri-plane Representation fo
 r Detailed Human Geometry and Appearance Synthesis
DESCRIPTION:Technical Papers\n\nHeming Zhu (Max Planck Institute for Infor
 matics, Saarland Informatics Campus); Fangneng Zhan (Max Planck Institute 
 for Informatics); and Christian Theobalt and Marc Habermann (Max Planck In
 stitute for Informatics; Saarbrücken Research Center for Visual Computing,
  Interaction and AI)\n\nCreating controllable, photorealistic, and geometr
 ically detailed digital doubles of real humans solely from video data is a
  key challenge in Computer Graphics and Vision, especially when real-time 
 performance is required. Recent methods attach a neural radiance field (Ne
 RF) to an articulated structure, e.g., a body model or a skeleton, to map 
 points into a pose canonical space while conditioning the NeRF on the skel
 etal pose. These approaches typically parameterize the neural field with a
  multi-layer perceptron (MLP) leading to a slow runtime. To address this d
 rawback, we propose TriHuman a novel human-tailored, deformable, and effic
 ient tri-plane representation, which achieves real-time performance, state
 -of-the-art pose-controllable geometry synthesis as well as photorealistic
  rendering quality. At the core, we non-rigidly warp global ray samples in
 to our undeformed tri-plane texture space, which effectively addresses the
  problem of global points being mapped to the same tri-plane locations. We
  then show how such a tri-plane feature representation can be conditioned 
 on the skeletal motion to account for dynamic appearance and geometry chan
 ges. Our results demonstrate a clear step towards higher quality in terms 
 of geometry and appearance modeling of humans and runtime performance.\n\n
 Registration Category: Full Access, Full Access Supporter\n\nLanguage Form
 at: English Language\n\nSession Chair: Manolis Savva (Simon Fraser Univers
 ity)
URL:https://asia.siggraph.org/2024/program/?id=tog_103&sess=sess136
END:VEVENT
END:VCALENDAR