ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision

TL;DR

ShadowNeuS introduces a novel shadow ray supervision method that enables neural SDF reconstruction from single-view images with shadows, improving shape recovery under various lighting conditions.

Contribution

It proposes a new shadow ray supervision scheme for neural SDF reconstruction from single-view images, including binary shadows and RGB data, under multiple lighting conditions.

Findings

Significant improvement over previous methods in shape reconstruction accuracy.

Effective reconstruction from single-view binary shadow images.

Extended capability to RGB images by modeling color-shadow correlations.

Abstract

By supervising camera rays between a scene and multi-view image planes, NeRF reconstructs a neural scene representation for the task of novel view synthesis. On the other hand, shadow rays between the light source and the scene have yet to be considered. Therefore, we propose a novel shadow ray supervision scheme that optimizes both the samples along the ray and the ray location. By supervising shadow rays, we successfully reconstruct a neural SDF of the scene from single-view images under multiple lighting conditions. Given single-view binary shadows, we train a neural network to reconstruct a complete scene not limited by the camera's line of sight. By further modeling the correlation between the image colors and the shadow rays, our technique can also be effectively extended to RGB inputs. We compare our method with previous works on challenging tasks of shape reconstruction from single-view binary shadow or RGB images and observe significant improvements. The code and data are available at https://github.com/gerwang/ShadowNeuS.