SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction
This addresses sparse-view surface reconstruction for 3D modeling applications, representing an incremental improvement over prior Gaussian splatting techniques.
The paper tackled the problem of reconstructing high-quality surfaces from sparse-view images using Gaussian splatting, and the result was superior performance on datasets like DTU, Tanks-and-Temples, and LLFF compared to existing methods.
Gaussian splatting has achieved impressive improvements for both novel-view synthesis and surface reconstruction from multi-view images. However, current methods still struggle to reconstruct high-quality surfaces from only sparse view input images using Gaussian splatting. In this paper, we propose a novel method called SolidGS to address this problem. We observed that the reconstructed geometry can be severely inconsistent across multi-views, due to the property of Gaussian function in geometry rendering. This motivates us to consolidate all Gaussians by adopting a more solid kernel function, which effectively improves the surface reconstruction quality. With the additional help of geometrical regularization and monocular normal estimation, our method achieves superior performance on the sparse view surface reconstruction than all the Gaussian splatting methods and neural field methods on the widely used DTU, Tanks-and-Temples, and LLFF datasets.