Depth-NeuS: Neural Implicit Surfaces Learning for Multi-view Reconstruction Based on Depth Information Optimization

TL;DR

Depth-NeuS introduces a novel neural implicit surface learning approach that incorporates depth information and geometric consistency to improve multi-view object reconstruction, especially for textured and low-texture surfaces.

Contribution

The paper proposes Depth-NeuS, a new method that explicitly uses depth data and geometric constraints to enhance neural implicit surface learning for better reconstruction.

Findings

Outperforms existing methods in multiple scenarios

Achieves high-quality surface reconstruction

Effectively models detailed surface features

Abstract

Recently, methods for neural surface representation and rendering, for example NeuS, have shown that learning neural implicit surfaces through volume rendering is becoming increasingly popular and making good progress. However, these methods still face some challenges. Existing methods lack a direct representation of depth information, which makes object reconstruction unrestricted by geometric features, resulting in poor reconstruction of objects with texture and color features. This is because existing methods only use surface normals to represent implicit surfaces without using depth information. Therefore, these methods cannot model the detailed surface features of objects well. To address this problem, we propose a neural implicit surface learning method called Depth-NeuS based on depth information optimization for multi-view reconstruction. In this paper, we introduce depth loss to explicitly constrain SDF regression and introduce geometric consistency loss to optimize for low-texture areas. Specific experiments show that Depth-NeuS outperforms existing technologies in multiple scenarios and achieves high-quality surface reconstruction in multiple scenarios.