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:20260114T163648Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T140000
DTEND;TZID=Australia/Melbourne:20231213T141000
UID:siggraphasia_SIGGRAPH Asia 2023_sess164_papers_183@linklings.com
SUMMARY:Towards Practical Capture of High-Fidelity Relightable Avatars
DESCRIPTION:Haotian Yang, Mingwu Zheng, Wanquan Feng, and Haibin Huang (Ku
 aishou Technology); Yu-Kun Lai (Cardiff University); and Pengfei Wan, Zhon
 gyuan Wang, and Chongyang Ma (Kuaishou Technology)\n\nIn this paper, we pr
 opose a novel framework, Tracking-free Relightable Avatar (TRAvatar), for 
 capturing and reconstructing high-fidelity 3D avatars. Compared to previou
 s methods, TRAvatar works in a more practical and efficient setting. Speci
 fically, TRAvatar is trained with dynamic image sequences captured in a Li
 ght Stage under varying lighting conditions, enabling realistic relighting
  and real-time animation for avatars in diverse scenes. Additionally, TRAv
 atar allows for tracking-free avatar capture and obviates the need for acc
 urate surface tracking under varying illumination conditions. Our contribu
 tions are two-fold: First, we propose a novel network architecture that ex
 plicitly builds on and ensures the satisfaction of the linear nature of li
 ghting. Trained on simple group light captures, TRAvatar can predict the a
 ppearance in real-time with a single forward pass, achieving high-quality 
 relighting effects under illuminations of arbitrary environment maps. Seco
 nd, we jointly optimize the facial geometry and relightable appearance fro
 m scratch based on image sequences, where the tracking is implicitly learn
 ed. This tracking-free approach brings robustness for establishing tempora
 l correspondences between frames under different lighting conditions. Exte
 nsive qualitative and quantitative experiments demonstrate that our framew
 ork achieves superior performance for photorealistic avatar animation and 
 relighting.\n\nRegistration Category: Full Access\n\nSession Chair: Parag 
 Chaudhuri (Indian Institute of Technology Bombay)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_183&sess=sess164
END:VEVENT
END:VCALENDAR