# Neural BRDF Representation and Importance Sampling arXiv: https://arxiv.org/abs/2102.05963 ยท HTML: https://mlsanity.com/paper/2102.05963/ ## Key facts - Cited by 28 papers in the map (data through 14 Oct 2026). - Builds on 11 of its 53 references that are in the map. - First posted on arXiv 11 Feb 2021. ## Builds on (most cited first, 11 of 11) - [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016) - [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014) - [AutoInt: Automatic Integration for Fast Neural Volume Rendering](https://mlsanity.com/paper/2012.01714/) (2020) - [Neural Importance Sampling](https://mlsanity.com/paper/1808.03856/) (2018) - [Single-Image SVBRDF Capture with a Rendering-Aware Deep Network](https://mlsanity.com/paper/1810.09718/) (2018) - [Invertible Neural BRDF for Object Inverse Rendering](https://mlsanity.com/paper/2008.04030/) (2020) - [Learning to Importance Sample in Primary Sample Space](https://mlsanity.com/paper/1808.07840/) (2018) - [Deep Appearance Maps](https://mlsanity.com/paper/1804.00863/) (2018) - [Gaussian Material Synthesis](https://mlsanity.com/paper/1804.08369/) (2018) - [Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks](https://mlsanity.com/paper/1709.05418/) (2017) - [Image-based remapping of spatially-varying material appearance](https://mlsanity.com/paper/1808.06715/) (2018) ## Built on by (most cited first, 28 of 28) - [Differentiable Point-Based Radiance Fields for Efficient View Synthesis](https://mlsanity.com/paper/2205.14330/) (2022) - [HyperTime: Implicit Neural Representation for Time Series](https://mlsanity.com/paper/2208.05836/) (2022) - [NeurMiPs: Neural Mixture of Planar Experts for View Synthesis](https://mlsanity.com/paper/2204.13696/) (2022) - [Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting](https://mlsanity.com/paper/2401.09126/) (2024) - [Generative World Renderer](https://mlsanity.com/paper/2604.02329/) (2026) - [Learning to Learn and Sample BRDFs](https://mlsanity.com/paper/2210.03510/) (2022) - [Neural Fields with Hard Constraints of Arbitrary Differential Order](https://mlsanity.com/paper/2306.08943/) (2023) - [NeuBTF: Neural fields for BTF encoding and transfer](https://mlsanity.com/paper/2307.01199/) (2023) - [Real-Time Neural BRDF with Spherically Distributed Primitives](https://mlsanity.com/paper/2310.08332/) (2023) - [Real-Time Neural Materials using Block-Compressed Features](https://mlsanity.com/paper/2311.16121/) (2023) - [Generating Parametric BRDFs from Natural Language Descriptions](https://mlsanity.com/paper/2306.15679/) (2023) - [MADS: Modulated Auto-Decoding SIREN for time series imputation](https://mlsanity.com/paper/2307.00868/) (2023) - [FROST-BRDF: A Fast and Robust Optimal Sampling Technique for BRDF Acquisition](https://mlsanity.com/paper/2401.07283/) (2024) - [Neural Product Importance Sampling via Warp Composition](https://mlsanity.com/paper/2409.18974/) (2024) - [Neural BRDF Importance Sampling by Reparameterization](https://mlsanity.com/paper/2505.08998/) (2025) - [On Neural BRDFs: A Thorough Comparison of State-of-the-Art Approaches](https://mlsanity.com/paper/2502.15480/) (2025) - [Neural BRDFs: Representation and Operations](https://mlsanity.com/paper/2111.03797/) (2021) - [Physically Based Neural Bidirectional Reflectance Distribution Function](https://mlsanity.com/paper/2411.02347/) (2024) - [FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting](https://mlsanity.com/paper/2511.23292/) (2025) - [Lunar-G2R: Geometry-to-Reflectance Learning for High-Fidelity Lunar BRDF Estimation](https://mlsanity.com/paper/2601.10449/) (2026) - [8DNA: 8D Neural Asset Light Transport by Distribution Learning](https://mlsanity.com/paper/2604.25129/) (2026) - [Neural Appearance Modeling From Single Images](https://mlsanity.com/paper/2406.18593/) (2024) - [GratNet: A Photorealistic Neural Shader for Diffractive Surfaces](https://mlsanity.com/paper/2506.15815/) (2025) - [FreNBRDF: A Frequency-Rectified Neural Material Representation](https://mlsanity.com/paper/2507.00476/) (2025) - [A Hybrid Neural-Microfacet BRDF Model for Real-Time Rendering](https://mlsanity.com/paper/2608.09604/) (2026) - [RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives](https://mlsanity.com/paper/2609.05738/) (2026) - [PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding](https://mlsanity.com/paper/2609.09020/) (2026) - [RoomLight: A 2.5D Illumination Prior for Indoor Environments](https://mlsanity.com/paper/2609.28300/) (2026) ## Abstract (arXiv) Controlled capture of real-world material appearance yields tabulated sets of highly realistic reflectance data. In practice, however, its high memory footprint requires compressing into a representation that can be used efficiently in rendering while remaining faithful to the original. Previous works in appearance encoding often prioritised one of these requirements at the expense of the other, by either applying high-fidelity array compression strategies not suited for efficient queries during rendering, or by fitting a compact analytic model that lacks expressiveness. We present a compact neural network-based representation of BRDF data that combines high-accuracy reconstruction with efficient practical rendering via built-in interpolation of reflectance. We encode BRDFs as lightweight networks, and propose a training scheme with adaptive angular sampling, critical for the accurate reconstruction of specular highlights. Additionally, we propose a novel approach to make our representation amenable to importance sampling: rather than inverting the trained networks, we learn to encode them in a more compact embedding that can be mapped to parameters of an analytic BRDF for which importance sampling is known. We evaluate encoding results on isotropic and anisotropic BRDFs from multiple real-world datasets, and importance sampling performance for isotropic BRDFs mapped to two different analytic models.