Presentation / Installation


Deep Appearance Prefiltering
SessionNeural Light Transport
DescriptionWe propose the first comprehensive multi-scale, level-of-detail framework for prefiltering 3D environments with complex geometry and materials using a novel neural representation that encodes appearance data into a compact latent form. Our approach compares favorably to state-of-the-art methods and achieves considerable savings in memory for complex scenes.
Authors
Steve Bako
University of California Santa Barbara
Pradeep Sen
University of California Santa Barbara
Anton Kaplanyan
Intel Graphics Research
Presenter
Steve Bako
Aurora Innovation
Event Type
Technical Paper
TimeTuesday, 8 August 20232pm - 2:11pm PDT
LocationRoom 502 AB
ACM Digital Library Technical Papers pdfs
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 Prefiltering for Correlation-aware Levels of Detail