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:20230103T035312Z
LOCATION:Room 324\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221209T140000
DTEND;TZID=Asia/Seoul:20221209T153000
UID:siggraphasia_SIGGRAPH Asia 2022_sess174_papers_422@linklings.com
SUMMARY:FloRen: Real-time High-quality Human Performance Rendering via App
 earance Flow Using Sparse RGB Cameras
DESCRIPTION:Technical Communications, Technical Papers\n\nFloRen: Real-tim
 e High-quality Human Performance Rendering via Appearance Flow Using Spars
 e RGB Cameras\n\nShao, Chen, Zheng, Zhang, Zhang...\n\nWe propose FloRen, 
 a novel system for real-time, high-resolution free-view human synthesis. O
 ur system runs at 15fps in 1K resolution with very sparse RGB cameras. In 
 FloRen, a coarse-level implicit geometry is recovered at first as initiali
 zation, and then processed by a neural rendering framework based on appear
 ance flow. Our appearance flow-based rendering framework consists of three
  steps, namely view-dependent depth refinement, appearance flow estimation
  and occlusion-aware color rendering. In this way, we resolve the view syn
 thesis problem in the image plane, where 2D convolutional neural networks 
 can be efficiently applied, contributing to high speed performance. For ro
 bust appearance flow estimation, we explicitly combine data-driven human p
 rior knowledge with multiview geometric constraints. The accurate appearan
 ce flow enables precise color 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 outperform
 s many offline methods.\n\nRegistration Category: FULL ACCESS, ON-DEMAND A
 CCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_422&sess=sess17
 4
END:VEVENT
END:VCALENDAR