AI RESEARCH
CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus
arXiv CS.CV
•
ArXi:2509.04859v3 Announce Type: replace Fast and efficient 3D reconstruction is essential for time-critical robotic applications such as tele-guidance and disaster response, where operators must rapidly analyze specific points of interest (POIs). Existing semantic Gaussian Splatting (GS) approaches optimize the entire scene uniformly, incurring substantial computational cost even when only a small subset of the scene is operationally relevant. We propose CoRe-GS, a coarse-to-refine GS framework that enables task-driven POI-focused optimization.