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:20241206T090000
DTEND;TZID=Asia/Tokyo:20241206T101000
UID:siggraphasia_SIGGRAPH Asia 2024_sess140@linklings.com
SUMMARY:Differentiable Rendering
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nA Simple Approach to Differentiable Rendering of SDFs\n\nWe present a 
 simple algorithm for differentiable rendering of surfaces represented by S
 igned Distance Fields (SDF), which makes it easy to integrate rendering in
 to gradient-based optimization pipelines. To tackle visibility-related der
 ivatives that make rendering non-differentiable, existing physica...\n\n\n
 Zichen Wang and Xi Deng (Cornell University), Ziyi Zhang and Wenzel Jakob 
 (EPFL), and Steve Marschner (Cornell University)\n---------------------\nM
 arkov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiab
 le Rendering\n\nPhysics-based differentiable rendering requires estimating
  boundary path integrals emerging from the shift of discontinuities (e.g.,
  visibility boundaries). Previously, although the mathematical formulation
  of boundary path integrals has been established, efficient and robust est
 imation of these int...\n\n\nPeiyu Xu (University of California Irvine); S
 ai Bangaru (MIT CSAIL, NVIDIA Research); Tzu-Mao Li (University of Califor
 nia San Diego); and Shuang Zhao (University of California Irvine)\n-------
 --------------\nDifferentiating Variance for Variance-Aware Inverse Render
 ing\n\nMonte Carlo methods have been widely adopted in physics-based rende
 ring.\n    A key property of a Monte Carlo estimator is its variance, whic
 h dictates the convergence rate of the estimator.\n    In this paper, we d
 evise a mathematical formulation for derivatives of rendering variance wit
 h respect to ...\n\n\nKai Yan (University of California Irvine, Wētā FX); 
 Vincent Pegoraro, Marc Droske, and Jiří Vorba (Wētā FX); and Shuang Zhao (
 University of California Irvine)\n---------------------\nNeural Differenti
 al Appearance Equations\n\nWe propose a method to reproduce dynamic appear
 ance textures with space-stationary but time-varying visual statistics.\nW
 hile most previous work decomposes dynamic textures into static appearance
  and motion, we focus on dynamic appearance that results not from motion b
 ut variations of fundamental pro...\n\n\nChen Liu and Tobias Ritschel (Uni
 versity College London (UCL))\n---------------------\nDifferentiable Photo
 n Mapping using Generalized Path Gradients\n\nPhoton mapping is a fundamen
 tal and practical Monte Carlo rendering technique for efficiently simulati
 ng global illumination effects, especially for caustics and specular-diffu
 se-specular (SDS) paths. In this paper, we present the first differentiabl
 e rendering method for photon mapping. The core of...\n\n\nJiankai Xing an
 d Zengyu Li (Tsinghua University), Fujun Luan (Adobe Research), and Kun Xu
  (Tsinghua University)\n---------------------\nDifferentiable Owen Scrambl
 ing\n\nQuasi-Monte Carlo integration is at the core of rendering. This tec
 hnique estimates the value of an integral by evaluating the integrand at w
 ell-chosen sample locations. These sample points are designed to cover the
  domain as uniformly as possible to achieve better convergence rates than 
 purely rand...\n\n\nBastien Doignies (Université Claude Bernard Lyon, LIRI
 S); David Coeurjolly, Nicolas Bonneel, and Julie Digne (CNRS, LIRIS); and 
 Jean-Claude Iehl and Victor Ostromoukhov (Université Claude Bernard Lyon, 
 LIRIS)\n\nRegistration Category: Full Access, Full Access Supporter\n\nLan
 guage Format: English Language\n\nSession Chair: Seungyong Lee (POSTECH)
END:VEVENT
END:VCALENDAR