ActiveNeuS: Neural Signed Distance Fields for Active Stereo

TL;DR

This paper introduces ActiveNeuS, a neural signed distance field approach for active stereo systems that enables high-quality 3D reconstruction in challenging environments like low light and underwater, using implicit correspondence search.

Contribution

It presents a novel neural SDF method for active stereo that simplifies system design and improves reconstruction in difficult conditions.

Findings

Achieves state-of-the-art reconstruction quality in low-light environments.

Successfully reconstructs textures and shapes underwater.

Operates effectively with a small number of images.

Abstract

3D-shape reconstruction in extreme environments, such as low illumination or scattering condition, has been an open problem and intensively researched. Active stereo is one of potential solution for such environments for its robustness and high accuracy. However, active stereo systems usually consist of specialized system configurations with complicated algorithms, which narrow their application. In this paper, we propose Neural Signed Distance Field for active stereo systems to enable implicit correspondence search and triangulation in generalized Structured Light. With our technique, textureless or equivalent surfaces by low light condition are successfully reconstructed even with a small number of captured images. Experiments were conducted to confirm that the proposed method could achieve state-of-the-art reconstruction quality under such severe condition. We also demonstrated that the proposed method worked in an underwater scenario.