Multi-view Normal and Distance Guidance Gaussian Splatting for Surface Reconstruction
This work addresses surface reconstruction challenges in multi-view scenes for applications like 3D modeling, but it is incremental as it builds upon existing 3D Gaussian Splatting methods.
The paper tackles the problem of view-dependent biases in 3D Gaussian Splatting for surface reconstruction by introducing multi-view normal and distance guidance, resulting in improved geometric depth unification and high-accuracy reconstruction that outperforms the baseline in quantitative and qualitative evaluations.
3D Gaussian Splatting (3DGS) achieves remarkable results in the field of surface reconstruction. However, when Gaussian normal vectors are aligned within the single-view projection plane, while the geometry appears reasonable in the current view, biases may emerge upon switching to nearby views. To address the distance and global matching challenges in multi-view scenes, we design multi-view normal and distance-guided Gaussian splatting. This method achieves geometric depth unification and high-accuracy reconstruction by constraining nearby depth maps and aligning 3D normals. Specifically, for the reconstruction of small indoor and outdoor scenes, we propose a multi-view distance reprojection regularization module that achieves multi-view Gaussian alignment by computing the distance loss between two nearby views and the same Gaussian surface. Additionally, we develop a multi-view normal enhancement module, which ensures consistency across views by matching the normals of pixel points in nearby views and calculating the loss. Extensive experimental results demonstrate that our method outperforms the baseline in both quantitative and qualitative evaluations, significantly enhancing the surface reconstruction capability of 3DGS. Our code will be made publicly available at (https://github.com/Bistu3DV/MND-GS/).