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:20241206T094600
DTEND;TZID=Asia/Tokyo:20241206T095800
UID:siggraphasia_SIGGRAPH Asia 2024_sess140_papers_551@linklings.com
SUMMARY:Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Dif
 ferentiable Rendering
DESCRIPTION:Technical Papers\n\nPeiyu Xu (University of California Irvine)
 ; Sai Bangaru (MIT CSAIL, NVIDIA Research); Tzu-Mao Li (University of Cali
 fornia San Diego); and Shuang Zhao (University of California Irvine)\n\nPh
 ysics-based differentiable rendering requires estimating boundary path int
 egrals emerging from the shift of discontinuities (e.g., visibility bounda
 ries). Previously, although the mathematical formulation of boundary path 
 integrals has been established, efficient and robust estimation of these i
 ntegrals has remained challenging. Specifically, state-of-the-art boundary
  sampling methods all rely on primary-sample-space guiding precomputed usi
 ng sophisticated data structures---whose performance tends to degrade for 
 finely tessellated geometries.\n\nIn this paper, we address this problem b
 y introducing} a new Markov-Chain-Monte-Carlo (MCMC) method. At the core o
 f our technique is a local perturbation step capable of efficiently explor
 ing highly fragmented primary sample spaces via specifically designed jump
 ing rules.\nWe compare the performance of our technique with several state
 -of-the-art baselines using synthetic differentiable-rendering and inverse
 -rendering experiments.\n\nRegistration Category: Full Access, Full Access
  Supporter\n\nLanguage Format: English Language\n\nSession Chair: Seungyon
 g Lee (POSTECH)
URL:https://asia.siggraph.org/2024/program/?id=papers_551&sess=sess140
END:VEVENT
END:VCALENDAR