Presentation / Installation


NeuSample: Importance Sampling for Neural Materials
SessionMaterial Rendering
DescriptionNeural materials show great promise, but the lack of effective importance sampling methods is a key limitation. We demonstrate three importance sampling methods: improved analytical mixtures, variations of normalizing flows, and histogram mixtures with novel designs. These approaches provide a toolbox for enabling spatially varying neural materials in production rendering.
Authors
Bing Xu
University of California San Diego
Liwen Wu
University of California San Diego
Milos Hasan
Adobe Research
Fujun Luan
Adobe Research
Iliyan Georgiev
Adobe Research
Zexiang Xu
Adobe Research
Ravi Ramamoorthi
University of California San Diego
Event Type
Technical Paper
TimeWednesday, 9 August 20232:33pm - 2:43pm PDT
LocationPetree Hall D
ACM Digital Library Technical Paper PDF
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Wednesday, 9 August 20232pm - 3:30pm PDTPetree Hall D
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Rendering
Video
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
Metameric: Spectral Uplifting via Controllable Color Constraints