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:20250110T023309Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241203T153100
DTEND;TZID=Asia/Tokyo:20241203T154300
UID:siggraphasia_SIGGRAPH Asia 2024_sess107_papers_296@linklings.com
SUMMARY:NeRF-Casting: Improved View-Dependent Appearance with Consistent R
 eflections
DESCRIPTION:Technical Papers\n\nDor Verbin, Pratul P. Srinivasan, Peter He
 dman, and Ben Mildenhall (Google Research); Benjamin Attal (Carnegie Mello
 n University); and Richard Szeliski and Jonathan T. Barron (Google Researc
 h)\n\nNeural Radiance Fields (NeRFs) typically struggle to reconstruct and
  render highly specular objects, whose appearance varies quickly with chan
 ges in viewpoint. Recent works have improved NeRF's ability to render deta
 iled specular appearance of distant environment illumination, but are unab
 le to synthesize consistent reflections of closer content. Moreover, these
  techniques rely on large computationally-expensive neural networks to mod
 el outgoing radiance, which severely limits optimization and rendering spe
 ed. We address these issues with an approach based on ray tracing: instead
  of querying an expensive neural network for the outgoing view-dependent r
 adiance at points along each camera ray, our model casts reflection rays f
 rom these points and traces them through the NeRF representation to render
  feature vectors which are decoded into color using a small inexpensive ne
 twork. We demonstrate that our model outperforms prior methods for view sy
 nthesis of scenes containing shiny objects, and that it is the only existi
 ng NeRF method that can synthesize photorealistic specular appearance and 
 reflections in real-world scenes, while requiring comparable optimization 
 time to current state-of-the-art view synthesis models.\n\nRegistration Ca
 tegory: Full Access, Full Access Supporter\n\nLanguage Format: English Lan
 guage\n\nSession Chair: Hongzhi Wu (Zhejiang University; State Key Laborat
 ory of CAD&CG, Zhejiang University)
URL:https://asia.siggraph.org/2024/program/?id=papers_296&sess=sess107
END:VEVENT
END:VCALENDAR