# Neural BRDF Importance Sampling by Reparameterization

arXiv: https://arxiv.org/abs/2505.08998 · HTML: https://mlsanity.com/paper/2505.08998/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 35 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 8 of 8)

- [Neural Importance Sampling](https://mlsanity.com/paper/1808.03856/) (2018)
- [Neural BRDF Representation and Importance Sampling](https://mlsanity.com/paper/2102.05963/) (2021)
- [Real-Time Neural Appearance Models](https://mlsanity.com/paper/2305.02678/) (2023)
- [NeuMIP: Multi-Resolution Neural Materials](https://mlsanity.com/paper/2104.02789/) (2021)
- [Path Guiding Using Spatio-Directional Mixture Models](https://mlsanity.com/paper/2111.13094/) (2021)
- [Neural BSSRDF: Object Appearance Representation Including Heterogeneous Subsurface Scattering](https://mlsanity.com/paper/2312.15711/) (2023)
- [Sampling Visible GGX Normals with Spherical Caps](https://mlsanity.com/paper/2306.05044/) (2023)
- [Neural Product Importance Sampling via Warp Composition](https://mlsanity.com/paper/2409.18974/) (2024)

## Built on by (most cited first, 3 of 3)

- [8DNA: 8D Neural Asset Light Transport by Distribution Learning](https://mlsanity.com/paper/2604.25129/) (2026)
- [PureLight: Learning Complex Luminaires with Light Tracing](https://mlsanity.com/paper/2606.04319/) (2026)
- [A Hybrid Neural-Microfacet BRDF Model for Real-Time Rendering](https://mlsanity.com/paper/2608.09604/) (2026)

## Abstract (arXiv)

Neural bidirectional reflectance distribution functions (BRDFs) have emerged as popular material representations for enhancing realism in physically-based rendering. Yet their importance sampling remains a significant challenge. In this paper, we introduce a reparameterization-based formulation of neural BRDF importance sampling that seamlessly integrates into the standard rendering pipeline with precise generation of BRDF samples. The reparameterization-based formulation transfers the distribution learning task to a problem of identifying BRDF integral substitutions. In contrast to previous methods that rely on invertible networks and multi-step inference to reconstruct BRDF distributions, our model removes these constraints, which offers greater flexibility and efficiency. Our variance and performance analysis demonstrates that our reparameterization method achieves the best variance reduction in neural BRDF renderings while maintaining high inference speeds compared to existing baselines.