NeRD: Neural Reflectance Decomposition from Image Collections

TL;DR

NeRD introduces a neural method for decomposing scenes into shape, reflectance, and illumination from image collections captured under various lighting conditions, enabling fast relightable 3D asset creation.

Contribution

It presents a novel neural reflectance decomposition approach that handles unconstrained illumination and converts learned models into real-time relightable meshes.

Findings

High-quality relightable 3D assets obtained from images

Effective decomposition under diverse lighting conditions

Fast rendering with novel illuminations

Abstract

Decomposing a scene into its shape, reflectance, and illumination is a challenging but important problem in computer vision and graphics. This problem is inherently more challenging when the illumination is not a single light source under laboratory conditions but is instead an unconstrained environmental illumination. Though recent work has shown that implicit representations can be used to model the radiance field of an object, most of these techniques only enable view synthesis and not relighting. Additionally, evaluating these radiance fields is resource and time-intensive. We propose a neural reflectance decomposition (NeRD) technique that uses physically-based rendering to decompose the scene into spatially varying BRDF material properties. In contrast to existing techniques, our input images can be captured under different illumination conditions. In addition, we also propose techniques to convert the learned reflectance volume into a relightable textured mesh enabling fast real-time rendering with novel illuminations. We demonstrate the potential of the proposed approach with experiments on both synthetic and real datasets, where we are able to obtain high-quality relightable 3D assets from image collections. The datasets and code is available on the project page: https://markboss.me/publication/2021-nerd/