BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171531Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241203T151900
DTEND;TZID=Asia/Tokyo:20241203T153100
UID:siggraphasia_SIGGRAPH Asia 2024_sess107_papers_162@linklings.com
SUMMARY:Reflection-Aware Neural Radiance Fields
DESCRIPTION:Chen Gao, Yipeng Wang, and Changil Kim (Meta); Jia-Bin Huang (
 University of Maryland, College Park); and Johannes Kopf (Meta)\n\nNeural 
 Radiance Fields (NeRF) have demonstrated exceptional capabilities in recon
 structing complex scenes with high fidelity. However, NeRF's view dependen
 cy can only handle low-frequency reflections. It falls short when handling
  complex planar reflections, often interpreting them as erroneous scene ge
 ometries and leading to duplicated and inaccurate scene representations. T
 o address this challenge, we introduce a reflection-aware NeRF that jointl
 y models planar reflectors, such as windows, and explicitly casts reflecte
 d rays to capture the source of the high-frequency reflections. We query a
  single radiance field to render the primary color and the source of the r
 eflection. We propose a sparse edge regularization to help utilize the tru
 e sources of reflections for rendering planar reflections rather than crea
 ting a duplicate along the primary ray at the same depth. As a result, we 
 obtain accurate scene geometry. Rendering along the primary ray results in
  a clean, reflection-free view, while explicitly rendering along the refle
 cted ray allows us to reconstruct highly detailed reflections. Our extensi
 ve quantitative and qualitative evaluations of real-world datasets demonst
 rate our method's enhanced performance in accurately handling reflections.
 \n\nRegistration Category: Full Access, Full Access Supporter\n\nLanguage 
 Format: English Language\n\nSession Chair: Hongzhi Wu (Zhejiang University
 ; State Key Laboratory of CAD&CG, Zhejiang University)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_162&sess=sess107
END:VEVENT
END:VCALENDAR