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:20240214T070241Z
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_646@linklings.com
SUMMARY:LitNeRF: Intrinsic Radiance Decomposition for High-Quality View Sy
 nthesis and Relighting of Faces
DESCRIPTION:Technical Papers\n\nKripasindhu Sarkar (Google Inc.); Marcel B
 ühler and Simon Li (ETH Zürich, Google Inc.); and Daoye Wang, Delio Vicini
 , Jérémy Riviere, Yinda Zhang, Sergio Orts-Escolano, Paulo Gotardo, Thabo 
 Beeler, and Abhimitra Meka (Google Inc.)\n\nHigh-fidelity, photorealistic 
 3D capture of a human face is a long-standing problem in computer graphics
  -- the complex material of skin, intricate geometry of hair, and fine sca
 le textural details make it challenging. Traditional techniques rely on ve
 ry large and expensive capture rigs to reconstruct explicit mesh geometry 
 and appearance maps and require complex differentiable path-tracing to ach
 ieve photorealistic results. More recent volumetric methods (\eg, NeRFs) h
 ave enabled view-synthesis and sometimes relighting by learning an implici
 t representation of the density and reflectance basis, but suffer from art
 ifacts and blurriness due to the inherent ambiguities in volumetric modeli
 ng. These problems are further exacerbated when capturing with few cameras
  and light sources. We present a novel technique for high-quality capture 
 of a human face for 3D view synthesis and relighting using a sparse, compa
 ct capture rig consisting of 15 cameras and 15 lights. Our method combines
  a volumetric representation of the face reflectance with traditional mult
 i-view stereo based geometry reconstruction. The proxy geometry allows us 
 to anchor the 3D density field to prevent artifacts and guide the disentan
 glement of intrinsic radiance components of the face appearance such as di
 ffuse and specular reflectance, and incident radiance (shadowing) fields. 
 \nOur hybrid representation significantly improves the state-of-the-art qu
 ality for arbitrarily dense renders of a face from desired camera viewpoin
 t as well as environmental, directional, and near-field lighting.\n\nRegis
 tration Category: Full Access, Enhanced Access, Trade Exhibitor, Experienc
 e Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_646&sess=sess209
END:VEVENT
END:VCALENDAR