文献类型：会议论文

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

作者：Chen, Shen[1];Zhou, Jiale[1];Li, Lei[2,3]

机构：[1]East China Univ Sci & Technol, Shanghai, Peoples R China;[2]Univ Washington, Seattle, WA 98195 USA;[3]Univ Copenhagen, Copenhagen, Denmark

会议论文集：2025 International Conference on Acoustics Speech and Signal Processing-ICASSP-Annual

会议日期：APR 06-11, 2025

会议地点：Hyderabad, INDIA

语种：英文

外文关键词：3D Gaussian Splatting; Novel View Synthesis; Sparse Viewpoints

摘要：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 DustGS, 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.