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:20260114T163652Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T152000
DTEND;TZID=Australia/Melbourne:20231213T153000
UID:siggraphasia_SIGGRAPH Asia 2023_sess125_papers_208@linklings.com
SUMMARY:SOL-NeRF: Sunlight Modeling for Outdoor Scene Decomposition and Re
 lighting
DESCRIPTION:Jia-Mu Sun and Tong Wu (Institute of Computing Technology, Chi
 nese Academy of Sciences; University of Chinese Academy of Sciences); Yong
 -Liang Yang (University of Bath); Yu-Kun Lai (Cardiff University); and Lin
  Gao (Institute of Computing Technology, Chinese Academy of Sciences; Univ
 ersity of Chinese Academy of Sciences)\n\nOutdoor scenes often involve lar
 ge-scale geometry and complex unknown lighting conditions, making it diffi
 cult to decompose them into geometry, reflectance and illumination. Recent
 ly researchers made attempts to decompose outdoor scenes using Neural Radi
 ance Fields (NeRF) and learning-based lighting and shadow representations.
  However, diverse lighting conditions and shadows in outdoor scenes are ch
 allenging for learning-based models. Moreover, existing methods may produc
 e rough geometry and normal reconstruction and introduce notable shading a
 rtifacts when the scene is rendered under a novel illumination. To solve t
 he above problems, we propose SOL-NeRF to decompose outdoor scenes with th
 e help of a hybrid lighting representation and a signed distance field geo
 metry reconstruction. We use a single Spherical Gaussian (SG) lobe to appr
 oximate the sun lighting, and a first-order Spherical Harmonic (SH) mixtur
 e to resemble the sky lighting. This hybrid representation is specifically
  designed for outdoor settings, and compactly models the outdoor lighting,
  ensuring robustness and efficiency. The shadow of the direct sun lighting
  can be obtained by casting the ray against the mesh extracted from the si
 gned distance field, and the remaining shadow can be approximated by Ambie
 nt Occlusion (AO). Additionally, sun lighting color prior and a relaxed Ma
 nhattan-world assumption can be further applied to boost decomposition and
  relighting performance. When changing the lighting condition, our method 
 can produce consistent relighting results with correct shadow effects. Exp
 eriments conducted on our hybrid lighting scheme and the entire decomposit
 ion pipeline show that our method achieves better reconstruction, decompos
 ition, and relighting performance compared to previous methods both quanti
 tatively and qualitatively.\n\nRegistration Category: Full Access\n\nSessi
 on Chair: Michael Gharbi (Reve AI, Massachusetts Institute of Technology (
 MIT))\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_208&sess=sess125
END:VEVENT
END:VCALENDAR