Relighting Neural Radiance Fields with Shadow and Highlight Hints

TL;DR

This paper introduces a neural implicit radiance model for relighting objects from few photographs, incorporating shadow and highlight hints to improve high-frequency light transport effects in relighting tasks.

Contribution

It proposes a novel neural implicit representation that models both shape and reflectance with shadow and highlight hints, enabling more accurate relighting from limited views.

Findings

Effective relighting on synthetic and real scenes

Handles complex shapes and materials

Improves modeling of high-frequency light effects

Abstract

This paper presents a novel neural implicit radiance representation for free viewpoint relighting from a small set of unstructured photographs of an object lit by a moving point light source different from the view position. We express the shape as a signed distance function modeled by a multi layer perceptron. In contrast to prior relightable implicit neural representations, we do not disentangle the different reflectance components, but model both the local and global reflectance at each point by a second multi layer perceptron that, in addition, to density features, the current position, the normal (from the signed distace function), view direction, and light position, also takes shadow and highlight hints to aid the network in modeling the corresponding high frequency light transport effects. These hints are provided as a suggestion, and we leave it up to the network to decide how to incorporate these in the final relit result. We demonstrate and validate our neural implicit representation on synthetic and real scenes exhibiting a wide variety of shapes, material properties, and global illumination light transport.