Dense Point Clouds Matter: Dust-GS for Scene Reconstruction from Sparse Viewpoints

TL;DR

Dust-GS is a novel framework that improves scene reconstruction from sparse viewpoints by introducing an effective point cloud initialization and depth-based masking, outperforming traditional 3D Gaussian Splatting methods.

Contribution

The paper proposes Dust-GS, a new method that enhances 3D scene reconstruction from sparse views by improving point cloud initialization and incorporating adaptive depth masking.

Findings

Dust-GS outperforms traditional 3DGS in sparse view scenarios.

It achieves higher reconstruction quality with fewer input images.

The approach demonstrates robustness across benchmark datasets.

Abstract

3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in scene synthesis and novel view synthesis tasks. Typically, the initialization of 3D Gaussian primitives relies on point clouds derived from Structure-from-Motion (SfM) methods. However, in scenarios requiring scene reconstruction from sparse viewpoints, the effectiveness of 3DGS is significantly constrained by the quality of these initial point clouds and the limited number of input images. In this study, we present Dust-GS, a novel framework specifically designed to overcome the limitations of 3DGS in sparse viewpoint conditions. Instead of relying solely on SfM, Dust-GS introduces an innovative point cloud initialization technique that remains effective even with sparse input data. Our approach leverages a hybrid strategy that integrates an adaptive depth-based masking technique, thereby enhancing the accuracy and detail of reconstructed scenes. Extensive experiments conducted on several benchmark datasets demonstrate that Dust-GS surpasses traditional 3DGS methods in scenarios with sparse viewpoints, achieving superior scene reconstruction quality with a reduced number of input images.