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:20260817T171516Z
LOCATION:Hall C\, C Block\, Level 4
DTSTART;TZID=Asia/Tokyo:20241203T090000
DTEND;TZID=Asia/Tokyo:20241203T120000
UID:siggraphasia_SIGGRAPH Asia 2024_sess223_papers_223@linklings.com
SUMMARY:A Simple Approach to Differentiable Rendering of SDFs
DESCRIPTION:Zichen Wang and Xi Deng (Cornell University), Ziyi Zhang and W
 enzel Jakob (EPFL), and Steve Marschner (Cornell University)\n\nWe present
  a simple algorithm for differentiable rendering of surfaces represented b
 y 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, existing physically ba
 sed differentiable rendering methods often rely on elaborate guiding data 
 structures or reparameterization with a global impact on variance. In this
  article, we investigate an alternative that embraces nonzero bias in exch
 ange for low variance and architectural simplicity. Our method expands the
  lower-dimensional boundary integral into a thin band that is easy to samp
 le when the underlying surface is represented by an SDF. We demonstrate th
 e performance and robustness of our formulation in end-to-end inverse rend
 ering tasks, where it obtains results that are competitive with or superio
 r to existing work.\n\nRegistration Category: Enhanced Access, Full Access
 , Full Access Supporter\n\nLanguage Format: English Language\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_223&sess=sess140
END:VEVENT
END:VCALENDAR