Neural Reflectance Fields for Appearance Acquisition

TL;DR

Neural Reflectance Fields provide a new deep scene representation that encodes detailed appearance properties at any 3D point, enabling realistic rendering and relighting of complex scenes from images.

Contribution

This work introduces Neural Reflectance Fields, a novel neural scene representation combined with differentiable rendering for accurate appearance modeling and relighting.

Findings

Accurately model complex real-world scene appearance

Enable high-quality view synthesis and relighting

Integrate with traditional rendering engines

Abstract

We present Neural Reflectance Fields, a novel deep scene representation that encodes volume density, normal and reflectance properties at any 3D point in a scene using a fully-connected neural network. We combine this representation with a physically-based differentiable ray marching framework that can render images from a neural reflectance field under any viewpoint and light. We demonstrate that neural reflectance fields can be estimated from images captured with a simple collocated camera-light setup, and accurately model the appearance of real-world scenes with complex geometry and reflectance. Once estimated, they can be used to render photo-realistic images under novel viewpoint and (non-collocated) lighting conditions and accurately reproduce challenging effects like specularities, shadows and occlusions. This allows us to perform high-quality view synthesis and relighting that is significantly better than previous methods. We also demonstrate that we can compose the estimated neural reflectance field of a real scene with traditional scene models and render them using standard Monte Carlo rendering engines. Our work thus enables a complete pipeline from high-quality and practical appearance acquisition to 3D scene composition and rendering.