Presentation / Installation


Parameter-space ReSTIR for Differentiable and Inverse Rendering
SessionInverse Rendering: Does Anybody Know How I Got Here?
DescriptionInverse rendering algorithms that utilize differentiable rendering typically use gradient descent to optimize for 3D scene parameters. We observe that the scene changes slowly during optimization, and therefore adapt temporal reuse from the ReSTIR algorithm in real-time rendering to reuse Monte Carlo samples across gradient iterations and accelerate inverse rendering.
Authors
Wesley Chang
University of California San Diego
Venkataram Sivaram
University of California San Diego
Derek Nowrouzezahrai
McGill University
Toshiya Hachisuka
University of Waterloo
Ravi Ramamoorthi
University of California San Diego
Tzu-Mao Li
University of California San Diego
Event Type
Technical Paper
TimeTuesday, 8 August 202311:28am - 11:38am PDT
LocationPetree Hall C
ACM Digital Library Technical Paper PDF
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Tuesday, 8 August 202310:45am - 12:15pm PDTPetree Hall C
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Rendering
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
Differentiable Heightfield Path Tracing With Accelerated Discontinuities