AI RESEARCH
Optimizing 3D Gaussian Splatting via Point Cloud Upsampling
arXiv CS.CV
•
ArXi:2606.00450v1 Announce Type: new 3D Gaussian Splatting (3DGS) is a technique for creating and rendering 3D scenes,. however. its performance depends heavily on the quality of initial seed points. To improve 3DGS initialization, this study presents and evaluates several point cloud upsampling approaches: linear interpolation, triangular interpolation, spline-based surface reconstruction, moving least squares surface fitting, and Voronoi-based point generation. Additionally, this research