Presentation

<
Rao-Blackwellized Markov chain Monte Carlo Light Transport
SessionLight Transport
DescriptionWe introduce a novel Rao-Blackwellization technique for variance reduction in Markov chain Monte Carlo light transport. We improve both Metropolis Light Transport and the current state-of-the-art, Jump Restore Light Transport, consistently outperforming traditional variance reduction, accelerating convergence, and establishing a new state-of-the-art in MCMC-based rendering under equal-time and equal-sample evaluations.
Authors
Sascha Holl
Max Planck Institute for Informatics
Saarland University
Gurprit Singh
Advanced Micro Devices (AMD)
Hans-Peter Seidel
Max Planck Institute for Informatics
Event Type
Technical Paper
TimeTuesday, 21 July 20262:20pm - 2:30pm PDT
LocationRoom 408 A
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Tuesday, 21 July 20262:00pm - 3:30pm PDTRoom 408 A
Keywords
Rendering
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationRagged Neighborhood Attention for Spatiotemporal Neural Denoising of Deep Monte Carlo Renderings
Similar Presentations
8DNA: 8D Neural Asset Light Transport by Distribution Learning
Sample Matching for Joint Extinction Gradient Estimation in Differentiable Volume Rendering
Differentiable Neutron Transport