CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus
This addresses the need for faster and higher-quality mobile reconstruction for time-critical tasks like tele-guidance and disaster response, though it is an incremental extension of Gaussian Splatting.
The paper tackles the problem of computationally expensive high-fidelity scene reconstruction for mobile applications by introducing CoRe-GS, a method that selectively refines semantically relevant points of interest, reducing training time to 25% compared to full semantic Gaussian Splatting while improving novel view synthesis quality in key areas.
Mobile reconstruction has the potential to support time-critical tasks such as tele-guidance and disaster response, where operators must quickly gain an accurate understanding of the environment. Full high-fidelity scene reconstruction is computationally expensive and often unnecessary when only specific points of interest (POIs) matter for timely decision making. We address this challenge with CoRe-GS, a semantic POI-focused extension of Gaussian Splatting (GS). Instead of optimizing every scene element uniformly, CoRe-GS first produces a fast segmentation-ready GS representation and then selectively refines splats belonging to semantically relevant POIs detected during data acquisition. This targeted refinement reduces training time to 25\% compared to full semantic GS while improving novel view synthesis quality in the areas that matter most. We validate CoRe-GS on both real-world (SCRREAM) and synthetic (NeRDS 360) datasets, demonstrating that prioritizing POIs enables faster and higher-quality mobile reconstruction tailored to operational needs.