BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_227@linklings.com
SUMMARY:NeuLighting: Neural Lighting for Free Viewpoint Outdoor Scene Reli
 ghting with Unconstrained Photo Collections
DESCRIPTION:Technical Papers\n\nNeuLighting: Neural Lighting for Free View
 point Outdoor Scene Relighting with Unconstrained Photo Collections\n\nLi,
  Guo, Fei, Li, Guo\n\nWe propose NeuLighting, a new framework for free vie
 wpoint outdoor scene relighting from a sparse set of unconstrained in-the-
 wild photo collections. Our framework represents all the scene components 
 as continuous functions parameterized by MLPs that take a 3D location and 
 the lighting condition as input and output reflectance and necessary outdo
 or illumination properties. Unlike object-level relighting methods which o
 ften leverage training images with controllable and consistent indoor illu
 mination, we concentrate on the more challenging outdoor situation where a
 ll the images are captured under arbitrary unknown illumination. The key t
 o our method includes a neural lighting representation that compresses the
  per-image illumination into a disentangled latent vector, and a new free 
 viewpoint relighting scheme that is robust to arbitrary lighting variation
 s across images. The lighting representation is compressive to explain a w
 ide range of illumination and can be easily fed into the query-based NeuLi
 ghting framework, enabling efficient shading effect evaluation under any k
 ind of novel illumination. Furthermore, to produce high-quality cast shado
 ws, we estimate the sun visibility map to indicate the shadow regions acco
 rding to the scene geometry and the sun direction. Thanks to the flexible 
 and explainable neural lighting representation, our system supports outdoo
 r relighting with many different illumination sources, including natural i
 mages, environment maps, and time-lapse videos. The high-fidelity renderin
 gs under novel views and illumination prove the superiority of our method 
 against state-of-the-art relighting solutions.\n\nRegistration Category: F
 ULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\n
 Language: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_227&sess=sess15
 3
END:VEVENT
END:VCALENDAR