Presentation / Installation


Denoising-aware Adaptive Sampling for Monte Carlo Ray Tracing
SessionNeural Light Transport
DescriptionWe present an adaptive sampling technique for Monte Carlo rendering when combined with learning-based denoisers. Our technique requires no additional learning and is based on a novel estimate of a neural network’s output variance. Applying this to pre-existing denoisers and recent consistent post-correction techniques, we achieve faster error convergence.
Authors
Arthur Firmino
Luxion
Technical University of Denmark
Jeppe Revall Frisvad
Technical University of Denmark
Henrik Wann Jensen
Luxion
Event Type
Technical Paper
TimeTuesday, 8 August 20232:52pm - 3:02pm PDT
LocationRoom 502 AB
ACM Digital Library Technical Paper PDF
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Tuesday, 8 August 20232pm - 3:30pm PDTRoom 502 AB
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Rendering
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
Neural Light Transport - Q&A and Interactive Discussion