FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency
This addresses a bottleneck in computer vision for applications requiring fast, high-quality 3D reconstruction from limited data, representing a strong incremental improvement.
The paper tackles the problem of surface reconstruction from sparse input views, where existing Gaussian Splatting methods degrade in quality, and achieves accurate reconstruction with a speedup of 60x to 200x compared to state-of-the-art methods.
Recently, Gaussian Splatting has sparked a new trend in the field of computer vision. Apart from novel view synthesis, it has also been extended to the area of multi-view reconstruction. The latest methods facilitate complete, detailed surface reconstruction while ensuring fast training speed. However, these methods still require dense input views, and their output quality significantly degrades with sparse views. We observed that the Gaussian primitives tend to overfit the few training views, leading to noisy floaters and incomplete reconstruction surfaces. In this paper, we present an innovative sparse-view reconstruction framework that leverages intra-view depth and multi-view feature consistency to achieve remarkably accurate surface reconstruction. Specifically, we utilize monocular depth ranking information to supervise the consistency of depth distribution within patches and employ a smoothness loss to enhance the continuity of the distribution. To achieve finer surface reconstruction, we optimize the absolute position of depth through multi-view projection features. Extensive experiments on DTU and BlendedMVS demonstrate that our method outperforms state-of-the-art methods with a speedup of 60x to 200x, achieving swift and fine-grained mesh reconstruction without the need for costly pre-training.