# Invertible Neural BRDF for Object Inverse Rendering

arXiv: https://arxiv.org/abs/2008.04030 · HTML: https://mlsanity.com/paper/2008.04030/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2020.

## Built on by (most cited first, 17 of 17)

- [Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition](https://mlsanity.com/paper/2110.14373/) (2021)
- [Differentiable Point-Based Radiance Fields for Efficient View Synthesis](https://mlsanity.com/paper/2205.14330/) (2022)
- [PANDORA: Polarization-Aided Neural Decomposition Of Radiance](https://mlsanity.com/paper/2203.13458/) (2022)
- [Neural BRDF Representation and Importance Sampling](https://mlsanity.com/paper/2102.05963/) (2021)
- [Intrinsic Neural Fields: Learning Functions on Manifolds](https://mlsanity.com/paper/2203.07967/) (2022)
- [Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting](https://mlsanity.com/paper/2401.09126/) (2024)
- [Neural Ray-Tracing: Learning Surfaces and Reflectance for Relighting and View Synthesis](https://mlsanity.com/paper/2104.13562/) (2021)
- [Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance](https://mlsanity.com/paper/2312.04529/) (2023)
- [nLMVS-Net: Deep Non-Lambertian Multi-View Stereo](https://mlsanity.com/paper/2207.11876/) (2022)
- [Fresnel Microfacet BRDF: Unification of Polari-Radiometric Surface-Body Reflection](https://mlsanity.com/paper/2212.04483/) (2022)
- [One Ring to Rule Them All: a simple solution to multi-view 3D-Reconstruction of shapes with unknown BRDF via a small Recurrent ResNet](https://mlsanity.com/paper/2104.05014/) (2021)
- [Generating Parametric BRDFs from Natural Language Descriptions](https://mlsanity.com/paper/2306.15679/) (2023)
- [FROST-BRDF: A Fast and Robust Optimal Sampling Technique for BRDF Acquisition](https://mlsanity.com/paper/2401.07283/) (2024)
- [DeepShaRM: Multi-View Shape and Reflectance Map Recovery Under Unknown Lighting](https://mlsanity.com/paper/2310.17632/) (2023)
- [Physically Accurate Differentiable Inverse Rendering for Radio Frequency Digital Twin](https://mlsanity.com/paper/2603.18026/) (2026)
- [Under One Sun: Multi-Object Generative Perception of Materials and Illumination](https://mlsanity.com/paper/2603.19226/) (2026)
- [ViDS: Video Diffusion Shader using 3D Face Tracking](https://mlsanity.com/paper/2607.24124/) (2026)

## Abstract (arXiv)

We introduce a novel neural network-based BRDF model and a Bayesian framework for object inverse rendering, i.e., joint estimation of reflectance and natural illumination from a single image of an object of known geometry. The BRDF is expressed with an invertible neural network, namely, normalizing flow, which provides the expressive power of a high-dimensional representation, computational simplicity of a compact analytical model, and physical plausibility of a real-world BRDF. We extract the latent space of real-world reflectance by conditioning this model, which directly results in a strong reflectance prior. We refer to this model as the invertible neural BRDF model (iBRDF). We also devise a deep illumination prior by leveraging the structural bias of deep neural networks. By integrating this novel BRDF model and reflectance and illumination priors in a MAP estimation formulation, we show that this joint estimation can be computed efficiently with stochastic gradient descent. We experimentally validate the accuracy of the invertible neural BRDF model on a large number of measured data and demonstrate its use in object inverse rendering on a number of synthetic and real images. The results show new ways in which deep neural networks can help solve challenging radiometric inverse problems.