BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070242Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_183@linklings.com
SUMMARY:Towards Practical Capture of High-Fidelity Relightable Avatars
DESCRIPTION:Technical Papers\n\nHaotian Yang, Mingwu Zheng, Wanquan Feng, 
 and Haibin Huang (Kuaishou Technology); Yu-Kun Lai (Cardiff University); a
 nd Pengfei Wan, Zhongyuan Wang, and Chongyang Ma (Kuaishou Technology)\n\n
 In this paper, we propose a novel framework, Tracking-free Relightable Ava
 tar (TRAvatar), for capturing and reconstructing high-fidelity 3D avatars.
  Compared to previous methods, TRAvatar works in a more practical and effi
 cient setting. Specifically, TRAvatar is trained with dynamic image sequen
 ces captured in a Light Stage under varying lighting conditions, enabling 
 realistic relighting and real-time animation for avatars in diverse scenes
 . Additionally, TRAvatar allows for tracking-free avatar capture and obvia
 tes the need for accurate surface tracking under varying illumination cond
 itions. Our contributions are two-fold: First, we propose a novel network 
 architecture that explicitly builds on and ensures the satisfaction of the
  linear nature of lighting. Trained on simple group light captures, TRAvat
 ar can predict the appearance in real-time with a single forward pass, ach
 ieving high-quality relighting effects under illuminations of arbitrary en
 vironment maps. Second, we jointly optimize the facial geometry and religh
 table appearance from scratch based on image sequences, where the tracking
  is implicitly learned. This tracking-free approach brings robustness for 
 establishing temporal correspondences between frames under different light
 ing conditions. Extensive qualitative and quantitative experiments demonst
 rate that our framework achieves superior performance for photorealistic a
 vatar animation and relighting.\n\nRegistration Category: Full Access, Enh
 anced Access, Trade Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_183&sess=sess209
END:VEVENT
END:VCALENDAR