BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_220@linklings.com
SUMMARY:Human Performance Modeling and Rendering via Neural Animated Mesh
DESCRIPTION:Technical Papers\n\nHuman Performance Modeling and Rendering v
 ia Neural Animated Mesh\n\nZhao, Jiang, Yao, Zhang, Wang...\n\nWe have rec
 ently seen tremendous progress in the neural advances for photo-real human
  modeling and rendering. But it's still challenging to integrate them into
  an existing mesh-based pipeline for downstream applications. In this pape
 r, we present a comprehensive neural approach for high-quality reconstruct
 ion, compression, and rendering of human performances from dense multi-vie
 w videos. Our core intuition is to bridge the traditional animated mesh wo
 rkflow with a new class of highly efficient neural techniques. We first in
 troduce a neural surface reconstructor for high-quality surface generation
  in minutes. It marries the implicit volumetric rendering of the truncated
  signed distance field (TSDF) with multi-resolution hash encoding. We furt
 her propose a hybrid neural tracker to generate animated meshes, which com
 bines explicit non-rigid tracking with implicit dynamic deformation in a s
 elf-supervised framework. The former provides the coarse warping back into
  the canonical space, while the latter implicit one further predicts the d
 isplacements using the 4D hash encoding as in our reconstructor. Then, we 
 discuss the rendering schemes using the obtained animated meshes, ranging 
 from dynamic texturing to lumigraph rendering under various bandwidth sett
 ings. To strike an intricate balance between quality and bandwidth, we pro
 pose a hierarchical solution by first rendering 6 virtual views covering t
 he performer and then conducting occlusion-aware neural texture blending. 
 We demonstrate the efficacy of our approach in a variety of mesh-based app
 lications and photo-realistic free-view experiences on various platforms, 
 i.e., inserting virtual human performances into real environments through 
 mobile AR or immersively watching talent shows with VR headsets.\n\nRegist
 ration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, T
 RADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_220&sess=sess15
 3
END:VEVENT
END:VCALENDAR