Presentation

<
Sample Matching for Joint Extinction Gradient Estimation in Differentiable Volume Rendering
SessionInverse Rendering
DescriptionWe propose sample matching, a variance reduction principle for differentiable volume rendering. By jointly estimating scattering and transmittance gradient components at shared sample positions, our method reduces gradient variance by up to 80%, significantly improving convergence speed and reconstruction quality in volumetric inverse rendering.
Authors
Ruihan Yu
The University of Tokyo
Tsinghua University
Yu-Chen Wang
University of California Irvine
Jingwang Ling
University of Illinois Urbana-Champaign
Feng Xu
Tsinghua University
Shuang Zhao
University of Illinois Urbana-Champaign
Event Type
Technical Paper
TimeThursday, 23 July 20269:40am - 9:50am PDT
LocationRoom 408 A
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Thursday, 23 July 20269:00am - 10:30am PDTRoom 408 A
Keywords
Lighting
Rendering
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationRobust Computation of Boundary Path Integrals Using Kernel-Density Estimation
Similar Presentations
Multi-feature Radiance Baking Neural Networks for Instant Volumetric Rendering
Gabor Fields: Orientation-Selective Level-of-Detail for Volume Rendering
Differentiable Neutron Transport