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:20230103T035311Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221208T140000
DTEND;TZID=Asia/Seoul:20221208T153000
UID:siggraphasia_SIGGRAPH Asia 2022_sess169_papers_220@linklings.com
SUMMARY:Human Performance Modeling and Rendering via Neural Animated Mesh
DESCRIPTION:Technical Communications, Technical Papers\n\nHuman Performanc
 e Modeling and Rendering via Neural Animated Mesh\n\nZhao, Jiang, Yao, Zha
 ng, Wang...\n\nWe have recently seen tremendous progress in the neural adv
 ances for photo-real human modeling and rendering. But it's still challeng
 ing to integrate them into an existing mesh-based pipeline for downstream 
 applications. In this paper, we present a comprehensive neural approach fo
 r high-quality reconstruction, compression, and rendering of human perform
 ances from dense multi-view videos. Our core intuition is to bridge the tr
 aditional animated mesh workflow with a new class of highly efficient neur
 al techniques. We first introduce 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-resolut
 ion hash encoding. We further propose a hybrid neural tracker to generate 
 animated meshes, which combines explicit non-rigid tracking with implicit 
 dynamic deformation in a self-supervised framework. The former provides th
 e coarse warping back into the canonical space, while the latter implicit 
 one further predicts the displacements using the 4D hash encoding as in ou
 r reconstructor. Then, we discuss the rendering schemes using the obtained
  animated meshes, ranging from dynamic texturing to lumigraph rendering un
 der various bandwidth settings. To strike an intricate balance between qua
 lity and bandwidth, we propose a hierarchical solution by first rendering 
 6 virtual views covering the performer and then conducting occlusion-aware
  neural texture blending. We demonstrate the efficacy of our approach in a
  variety of mesh-based applications and photo-realistic free-view experien
 ces on various platforms, i.e., inserting virtual human performances into 
 real environments through mobile AR or immersively watching talent shows w
 ith VR headsets.\n\nRegistration Category: FULL ACCESS, ON-DEMAND ACCESS\n
 \nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_220&sess=sess16
 9
END:VEVENT
END:VCALENDAR