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:20260114T163659Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T181900
DTEND;TZID=Australia/Melbourne:20231213T182900
UID:siggraphasia_SIGGRAPH Asia 2023_sess127_papers_646@linklings.com
SUMMARY:LitNeRF: Intrinsic Radiance Decomposition for High-Quality View Sy
 nthesis and Relighting of Faces
DESCRIPTION:Kripasindhu Sarkar (Google Inc.); Marcel Bühler and Simon Li (
 ETH Zürich, Google Inc.); and Daoye Wang, Delio Vicini, Jérémy Riviere, Yi
 nda Zhang, Sergio Orts-Escolano, Paulo Gotardo, Thabo Beeler, and Abhimitr
 a Meka (Google Inc.)\n\nHigh-fidelity, photorealistic 3D capture of a huma
 n face is a long-standing problem in computer graphics -- the complex mate
 rial of skin, intricate geometry of hair, and fine scale textural details 
 make it challenging. Traditional techniques rely on very large and expensi
 ve capture rigs to reconstruct explicit mesh geometry and appearance maps 
 and require complex differentiable path-tracing to achieve photorealistic 
 results. More recent volumetric methods (\eg, NeRFs) have enabled view-syn
 thesis and sometimes relighting by learning an implicit representation of 
 the density and reflectance basis, but suffer from artifacts and blurrines
 s due to the inherent ambiguities in volumetric modeling. These problems a
 re 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, compact capture rig consi
 sting of 15 cameras and 15 lights. Our method combines a volumetric repres
 entation of the face reflectance with traditional multi-view stereo based 
 geometry reconstruction. The proxy geometry allows us to anchor the 3D den
 sity field to prevent artifacts and guide the disentanglement of intrinsic
  radiance components of the face appearance such as diffuse and specular r
 eflectance, and incident radiance (shadowing) fields. \nOur hybrid represe
 ntation significantly improves the state-of-the-art quality for arbitraril
 y dense renders of a face from desired camera viewpoint as well as environ
 mental, directional, and near-field lighting.\n\nRegistration Category: Fu
 ll Access\n\nSession Chair: Jernej Barbic (University of Southern Californ
 ia)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_646&sess=sess127
END:VEVENT
END:VCALENDAR