BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171531Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T114300
DTEND;TZID=Asia/Tokyo:20241206T115400
UID:siggraphasia_SIGGRAPH Asia 2024_sess143_papers_796@linklings.com
SUMMARY:URAvatar: Universal Relightable Gaussian Codec Avatars
DESCRIPTION:Junxuan Li, Chen Cao, Gabriel Schwartz, Rawal Khirodkar, Chris
 tian Richardt, Tomas Simon, Yaser Sheikh, and Shunsuke Saito (Reality Labs
  Research)\n\nWe present a new approach to creating photorealistic and rel
 ightable head avatars from a phone scan with unknown illumination. The rec
 onstructed avatars can be animated and relit in real time with the global 
 illumination of diverse environments. Unlike existing approaches that esti
 mate parametric reflectance parameters via inverse rendering, our approach
  directly models learnable radiance transfer that incorporates global ligh
 t transport in an efficient manner for real-time rendering. However, learn
 ing such a complex light transport that can generalize across identities i
 s non-trivial. A phone scan in a single environment lacks sufficient infor
 mation to infer how the head would appear in general environments. To addr
 ess this, we build a universal relightable avatar model represented by 3D 
 Gaussians. We train on hundreds of high-quality multi-view human scans wit
 h controllable point lights.\nHigh-resolution geometric guidance further e
 nhances the reconstruction accuracy and generalization. Once trained, we f
 inetune the pretrained model on a phone scan using inverse rendering to ob
 tain a personalized relightable avatar. Our experiments establish the effi
 cacy of our design, outperforming existing approaches while retaining real
 -time rendering capability.\n\nRegistration Category: Full Access, Full Ac
 cess Supporter\n\nLanguage Format: English Language\n\nSession Chair: Iain
  Matthews (Epic Games, Carnegie Mellon University)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_796&sess=sess143
END:VEVENT
END:VCALENDAR