Depth-NeuS: Neural Implicit Surfaces Learning for Multi-view Reconstruction Based on Depth Information Optimization
This work addresses a specific challenge in 3D reconstruction for computer vision applications, representing an incremental improvement over prior methods.
The paper tackles the problem of poor reconstruction of objects with texture and color features in neural implicit surface learning by proposing Depth-NeuS, which introduces depth loss and geometric consistency loss to optimize multi-view reconstruction, resulting in outperforming existing technologies in multiple scenarios.
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.