CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914381942489088 |
|---|---|
| author | Schieber, Hannah Frischmann, Dominik Schaack, Victor Boche, Simon Schoellig, Angela Leutenegger, Stefan Roth, Daniel |
| author_facet | Schieber, Hannah Frischmann, Dominik Schaack, Victor Boche, Simon Schoellig, Angela Leutenegger, Stefan Roth, Daniel |
| contents | 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. Our method first produces a segmentation-ready GS representation using a lightweight late-stage semantic refinement. Subsequently, only Gaussians associated with the selected POI are further optimized, reducing unnecessary background computation. To mitigate segmentation-induced outliers (floaters) during selective refinement, we introduce a color-based filtering mechanism that removes inconsistent Gaussians without requiring mask rasterization. We evaluate robustness multiple datasets. On LERF-Mask, our segmentation-ready representation achieves competitive mIoU using tremendously fewer optimization steps. Across synthetic and real-world datasets (NeRDS360, SCRREAM, Tanks and Temples), CoRe-GS drastically reduces training time compared to full semantic GS while improving POI reconstruction quality and mitigating floaters. These results demonstrate that task-aware selective refinement enables faster and higher-quality scene reconstruction tailored to robotic operational needs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04859 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus Schieber, Hannah Frischmann, Dominik Schaack, Victor Boche, Simon Schoellig, Angela Leutenegger, Stefan Roth, Daniel Computer Vision and Pattern Recognition 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. Our method first produces a segmentation-ready GS representation using a lightweight late-stage semantic refinement. Subsequently, only Gaussians associated with the selected POI are further optimized, reducing unnecessary background computation. To mitigate segmentation-induced outliers (floaters) during selective refinement, we introduce a color-based filtering mechanism that removes inconsistent Gaussians without requiring mask rasterization. We evaluate robustness multiple datasets. On LERF-Mask, our segmentation-ready representation achieves competitive mIoU using tremendously fewer optimization steps. Across synthetic and real-world datasets (NeRDS360, SCRREAM, Tanks and Temples), CoRe-GS drastically reduces training time compared to full semantic GS while improving POI reconstruction quality and mitigating floaters. These results demonstrate that task-aware selective refinement enables faster and higher-quality scene reconstruction tailored to robotic operational needs. |
| title | CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.04859 |