PureSample: Neural Materials Learned by Sampling Microgeometry
Open Access
- 19 July 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Abstract
Traditional physically-based material models rely on analytically derived bidirectional reflectance distribution functions (BRDFs), typically by considering statistics of micro-primitives such as facets, flakes, or spheres, sometimes combined with multi-bounce interactions such as layering and multiple scattering. These derivations are often complex and model-specific. Once an analytic BRDF evaluation is defined, one still needs to design an importance sampling method for it and evaluate the probability density function (pdf) of that sampling distribution, requiring further model-specific derivations. We present PureSample: a novel neural BRDF representation that allows learning a material’s appearance purely by sampling forward random walks on the microgeometry, which is usually straightforward to implement. Our representation allows for efficient BRDF evaluation, importance sampling, and pdf evaluation, for homogeneous as well as spatially varying materials. We achieve this by two learnable components: first, the sampling distribution is modeled using a flow matching neural network, which allows both importance sampling and pdf evaluation; second, we introduce a view-dependent albedo term, captured by a lightweight neural network, which allows for converting a pdf value to a BRDF value for any pair of view and light directions. We demonstrate PureSample on challenging materials, including various microgeometries, multi-layered materials, and multiple-scattering microfacet materials.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62572230)
This publication has 49 references indexed in Scilit:
- VMF Diffuse: A unified rough diffuse BRDFComputer Graphics Forum, 2024
- Real-Time Neural BRDF with Spherically Distributed Primitives2024
- A Position‐Free Path Integral for Homogeneous Slabs and Multiple Scattering on Smith MicrofacetsComputer Graphics Forum, 2022
- Neural BRDF Representation and Importance SamplingComputer Graphics Forum, 2021
- Learning-Based Inverse Bi-Scale Material Fitting From Tabular BRDFsIEEE Transactions on Visualization and Computer Graphics, 2020
- An Efficient Transport Estimator for Complex Layered MaterialsComputer Graphics Forum, 2020
- Unified Neural Encoding of BTFsComputer Graphics Forum, 2020
- DeepBRDF: A Deep Representation for Manipulating Measured BRDFComputer Graphics Forum, 2020
- Gaussian Product Sampling for Rendering Layered MaterialsComputer Graphics Forum, 2019
- Neural BTF Compression and InterpolationComputer Graphics Forum, 2019