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:20260817T171533Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T093400
DTEND;TZID=Asia/Tokyo:20241206T094600
UID:siggraphasia_SIGGRAPH Asia 2024_sess140_papers_717@linklings.com
SUMMARY:Differentiable Photon Mapping using Generalized Path Gradients
DESCRIPTION:Jiankai Xing and Zengyu Li (Tsinghua University), Fujun Luan (
 Adobe Research), and Kun Xu (Tsinghua University)\n\nPhoton mapping is a f
 undamental and practical Monte Carlo rendering technique for efficiently s
 imulating global illumination effects, especially for caustics and specula
 r-diffuse-specular (SDS) paths. In this paper, we present the first differ
 entiable rendering method for photon mapping. The core of our method is a 
 newly introduced concept named generalized path gradients. Based on the ex
 tended path space manifolds (EPSMs), the generalized path gradients define
  the derivatives of the vertex positions and color contributions of a path
  with respect to scene parameters under given geometric constraints. By fo
 rmalizing photon mapping as a path sampling technique through vertex mergi
 ng and incorporating a smooth differentiable density estimation kernel, we
  enable the differentiation of the photon mapping algorithms based on the 
 theoretical results of generalized path gradients. Experiments demonstrate
  that our method is more effective than state-of-the-art physics-based dif
 ferentiable rendering methods in inverse rendering applications in handlin
 g difficult illumination paths, especially SDS paths.\n\nRegistration Cate
 gory: Full Access, Full Access Supporter\n\nLanguage Format: English Langu
 age\n\nSession Chair: Seungyong Lee (POSTECH)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_717&sess=sess140
END:VEVENT
END:VCALENDAR