BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260805T205516Z
LOCATION:Room 408 A
DTSTART;TZID=America/Los_Angeles:20260723T090000
DTEND;TZID=America/Los_Angeles:20260723T103000
UID:siggraph_SIGGRAPH 2026_sess133@linklings.com
SUMMARY:Inverse Rendering
DESCRIPTION:Inverse Rendering for Discrete X-Ray Computed Tomography\n\nWe
  propose a gradient-based discrete tomography method that models each voxe
 l as a probability distribution over known materials, minimizing an object
 -space loss for projection consistency. Inspired by inverse rendering, it 
 outperforms classical methods, supports scattering, and excels in sparse a
 nd...\n\n\nLovro Nuic and Ziyi Zhang (Ecole Polytechnique Fédérale de Laus
 anne), Korbinian Sager (Carl Zeiss AG), and Wenzel Jakob (Ecole Polytechni
 que Fédérale de Lausanne)\n---------------------\nAmbient-robust Inverse R
 endering using Robot-assisted RGB-NIR Imaging\n\nThis paper presents an am
 bient-robust inverse rendering method using robot-assisted RGB–NIR imaging
 . By combining multi-view RGB images with NIR flash images, we reconstruct
  accurate geometry and reflectance under multiple lighting conditions. We 
 also introduce a robot-assisted imaging system ...\n\n\nHoon-Gyu Chung, Ji
 nnyeong Kim, Hyunwoo Kang, and Seung-Hwan Baek (POSTECH)\n----------------
 -----\nEAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoo
 r Scene Reconstruction and Editing\n\nEAG-PT reconstructs indoor scenes wi
 th 2D Gaussians for editable diffuse global illumination. By separating em
 issive and non-emissive components and combining efficient reconstruction 
 with path tracing, it enables more natural, physically consistent scene ed
 iting than radiance-field methods, while a...\n\n\nXijie Yang (Zhejiang Un
 iversity, Shanghai Artificial Intelligence Laboratory); Mulin Yu (Shanghai
  Artificial Intelligence Laboratory); Changjian Jiang (Zhejiang University
 ); Kerui Ren (Shanghai Jiao Tong University, Shanghai Artificial Intellige
 nce Laboratory); Tao Lu and Jiangmiao Pang (Shanghai Artificial Intelligen
 ce Laboratory); Dahua Lin (The Chinese University of Hong Kong, Shanghai A
 rtificial Intelligence Laboratory); Bo Dai (The University of Hong Kong, F
 eeling AI); and Linning Xu (The Chinese University of Hong Kong, Shanghai 
 Artificial Intelligence Laboratory)\n---------------------\nRadiance Cachi
 ng for Differentiable Path Tracing\n\nWe introduce a spatially blended rad
 iance-caching framework for differentiable path tracing that improves spee
 d and robustness in material recovery under unknown lighting. \nBy jointly
  optimizing cache, materials, and blending, the method produces physically
  meaningful materials that generalize to ne...\n\n\nZiyi Zhang (Google, Éc
 ole Polytechnique Féderale de Lausanne (EPFL)); Delio Vicini, Sebastian Wi
 nberg, and Stephan Garbin (Google); and Wenzel Jakob (Ecole Polytechnique 
 Fédérale de Lausanne)\n---------------------\nSample Matching for Joint Ex
 tinction Gradient Estimation in Differentiable Volume Rendering\n\nWe prop
 ose sample matching, a variance reduction principle for differentiable vol
 ume rendering. By jointly estimating scattering and transmittance gradient
  components at shared sample positions, our method reduces gradient varian
 ce by up to 80%, significantly improving convergence speed and reconstr...
 \n\n\nRuihan Yu (The University of Tokyo, Tsinghua University); Yu-Chen Wa
 ng (University of California Irvine); Jingwang Ling (University of Illinoi
 s Urbana-Champaign); Feng Xu (Tsinghua University); and Shuang Zhao (Unive
 rsity of Illinois Urbana-Champaign)\n---------------------\nRobust Computa
 tion of Boundary Path Integrals Using Kernel-Density Estimation\n\nWe pres
 ent a simple, robust, and consistent estimator for boundary path integrals
  in physics-based differentiable rendering. By reformulating boundary inte
 gration with kernel-density estimation, our method avoids fragile measure-
 zero sampling and costly reparameterization. It matches finite-differen...
 \n\n\nPeiyu Xu (University of Illinois Urbana-Champaign); Lifan Wu and Ben
 edikt Bitterli (NVIDIA); Ravi Ramamoorthi (NVIDIA, University of Californi
 a San Diego); and Shuang Zhao (University of Illinois Urbana-Champaign)\n-
 --------------------\nInverse Rendering - Interactive Discussion\n\nAfter 
 the summary presentations, attendees will participate in an interactive di
 scussion. Outside the room will be a series of poster boards for authors t
 o gather around with the audience. Authors are invited to bring any materi
 al related to their paper that could instigate further conversation such..
 .\n\n\nInterest Area: Research & Education\n\nKeyword: Lighting, Modeling,
  Rendering\n\nRegistration Category: Full Conference Supporter, Full Confe
 rence\n\nSession Chair: David Hahn (Technische Universität Wien (TU Wien))
END:VEVENT
END:VCALENDAR