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:20230103T035306Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_422@linklings.com
SUMMARY:FloRen: Real-time High-quality Human Performance Rendering via App
 earance Flow Using Sparse RGB Cameras
DESCRIPTION:Technical Papers\n\nFloRen: Real-time High-quality Human Perfo
 rmance Rendering via Appearance Flow Using Sparse RGB Cameras\n\nShao, Che
 n, Zheng, Zhang, Zhang...\n\nWe propose FloRen, a novel system for real-ti
 me, high-resolution free-view human synthesis. Our system runs at 15fps in
  1K resolution with very sparse RGB cameras. In FloRen, a coarse-level imp
 licit geometry is recovered at first as initialization, and then processed
  by a neural rendering framework based on appearance flow. Our appearance 
 flow-based rendering framework consists of three steps, namely view-depend
 ent depth refinement, appearance flow estimation and occlusion-aware color
  rendering. In this way, we resolve the view synthesis problem in the imag
 e plane, where 2D convolutional neural networks can be efficiently applied
 , contributing to high speed performance. For robust appearance flow estim
 ation, we explicitly combine data-driven human prior knowledge with multiv
 iew geometric constraints. The accurate appearance flow enables precise co
 lor mapping from input view to novel view, which greatly facilitates high-
 resolution novel view generation. We demonstrate that our system achieves 
 state-of-the-art performance and even outperforms many offline methods.\n\
 nRegistration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE AC
 CESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_422&sess=sess15
 3
END:VEVENT
END:VCALENDAR