PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields

TL;DR

PBR-NeRF introduces a physics-based inverse rendering approach that jointly estimates scene geometry, materials, and illumination, improving material accuracy while maintaining high-quality view synthesis.

Contribution

It presents a novel inverse rendering model with physics-based priors for better material and illumination estimation in neural radiance fields.

Findings

State-of-the-art material estimation accuracy.

Maintains high-quality novel view synthesis.

Flexible adaptation to other inverse rendering frameworks.

Abstract

We tackle the ill-posed inverse rendering problem in 3D reconstruction with a Neural Radiance Field (NeRF) approach informed by Physics-Based Rendering (PBR) theory, named PBR-NeRF. Our method addresses a key limitation in most NeRF and 3D Gaussian Splatting approaches: they estimate view-dependent appearance without modeling scene materials and illumination. To address this limitation, we present an inverse rendering (IR) model capable of jointly estimating scene geometry, materials, and illumination. Our model builds upon recent NeRF-based IR approaches, but crucially introduces two novel physics-based priors that better constrain the IR estimation. Our priors are rigorously formulated as intuitive loss terms and achieve state-of-the-art material estimation without compromising novel view synthesis quality. Our method is easily adaptable to other inverse rendering and 3D reconstruction frameworks that require material estimation. We demonstrate the importance of extending current neural rendering approaches to fully model scene properties beyond geometry and view-dependent appearance. Code is publicly available at https://github.com/s3anwu/pbrnerf