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:20250110T023313Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T095800
DTEND;TZID=Asia/Tokyo:20241206T100900
UID:siggraphasia_SIGGRAPH Asia 2024_sess140_papers_223@linklings.com
SUMMARY:A Simple Approach to Differentiable Rendering of SDFs
DESCRIPTION:Technical Papers\n\nZichen Wang and Xi Deng (Cornell Universit
 y), Ziyi Zhang and Wenzel Jakob (EPFL), and Steve Marschner (Cornell Unive
 rsity)\n\nWe present a simple algorithm for differentiable rendering of su
 rfaces represented by Signed Distance Fields (SDF), which makes it easy to
  integrate rendering into gradient-based optimization pipelines. To tackle
  visibility-related derivatives that make rendering non-differentiable, ex
 isting physically based differentiable rendering methods often rely on ela
 borate guiding data structures or reparameterization with a global impact 
 on variance. In this article, we investigate an alternative that embraces 
 nonzero bias in exchange for low variance and architectural simplicity. Ou
 r method expands the lower-dimensional boundary integral into a thin band 
 that is easy to sample when the underlying surface is represented by an SD
 F. We demonstrate the performance and robustness of our formulation in end
 -to-end inverse rendering tasks, where it obtains results that are competi
 tive with or superior to existing work.\n\nRegistration Category: Full Acc
 ess, Full Access Supporter\n\nLanguage Format: English Language\n\nSession
  Chair: Seungyong Lee (POSTECH)
URL:https://asia.siggraph.org/2024/program/?id=papers_223&sess=sess140
END:VEVENT
END:VCALENDAR