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:20240214T070242Z
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_208@linklings.com
SUMMARY:SOL-NeRF: Sunlight Modeling for Outdoor Scene Decomposition and Re
 lighting
DESCRIPTION:Technical Papers\n\nJia-Mu Sun and Tong Wu (Institute of Compu
 ting Technology, Chinese Academy of Sciences; University of Chinese Academ
 y of Sciences); Yong-Liang Yang (University of Bath); Yu-Kun Lai (Cardiff 
 University); and Lin Gao (Institute of Computing Technology, Chinese Acade
 my of Sciences; University of Chinese Academy of Sciences)\n\nOutdoor scen
 es often involve large-scale geometry and complex unknown lighting conditi
 ons, making it difficult to decompose them into geometry, reflectance and 
 illumination. Recently researchers made attempts to decompose outdoor scen
 es using Neural Radiance Fields (NeRF) and learning-based lighting and sha
 dow representations. However, diverse lighting conditions and shadows in o
 utdoor scenes are challenging for learning-based models. Moreover, existin
 g methods may produce rough geometry and normal reconstruction and introdu
 ce notable shading artifacts when the scene is rendered under a novel illu
 mination. To solve the above problems, we propose SOL-NeRF to decompose ou
 tdoor scenes with the help of a hybrid lighting representation and a signe
 d distance field geometry reconstruction. We use a single Spherical Gaussi
 an (SG) lobe to approximate the sun lighting, and a first-order Spherical 
 Harmonic (SH) mixture to resemble the sky lighting. This hybrid representa
 tion is specifically designed for outdoor settings, and compactly models t
 he outdoor lighting, ensuring robustness and efficiency. The shadow of the
  direct sun lighting can be obtained by casting the ray against the mesh e
 xtracted from the signed distance field, and the remaining shadow can be a
 pproximated by Ambient Occlusion (AO). Additionally, sun lighting color pr
 ior and a relaxed Manhattan-world assumption can be further applied to boo
 st decomposition and relighting performance. When changing the lighting co
 ndition, our method can produce consistent relighting results with correct
  shadow effects. Experiments conducted on our hybrid lighting scheme and t
 he entire decomposition pipeline show that our method achieves better reco
 nstruction, decomposition, and relighting performance compared to previous
  methods both quantitatively and qualitatively.\n\nRegistration Category: 
 Full Access, Enhanced Access, Trade Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_208&sess=sess209
END:VEVENT
END:VCALENDAR