AI RESEARCH
High-Fidelity Surface Splatting-Based 3D Reconstruction from Multi-View Images
arXiv CS.CV
•
ArXi:2605.07254v1 Announce Type: new Multi-view mesh reconstruction remains a core challenge in computer graphics and vision, especially for recovering high-frequency geometry from sparse observations. Recent methods such as 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) rely on post-processing for mesh extraction, thereby limiting joint optimization of geometry and appearance. Implicit Moving Least Squares (IMLS) instead enables direct conversion of point clouds into signed distance and texture fields, ing end-to-end reconstruction and rendering.