ROI-GS: Interest-based Local Quality 3D Gaussian Splatting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909851837267968 |
|---|---|
| author | Bui, Quoc-Anh Rougeron, Gilles Morin, Géraldine Gasparini, Simone |
| author_facet | Bui, Quoc-Anh Rougeron, Gilles Morin, Géraldine Gasparini, Simone |
| contents | We tackle the challenge of efficiently reconstructing 3D scenes with high detail on objects of interest. Existing 3D Gaussian Splatting (3DGS) methods allocate resources uniformly across the scene, limiting fine detail to Regions Of Interest (ROIs) and leading to inflated model size. We propose ROI-GS, an object-aware framework that enhances local details through object-guided camera selection, targeted Object training, and seamless integration of high-fidelity object of interest reconstructions into the global scene. Our method prioritizes higher resolution details on chosen objects while maintaining real-time performance. Experiments show that ROI-GS significantly improves local quality (up to 2.96 dB PSNR), while reducing overall model size by $\approx 17\%$ of baseline and achieving faster training for a scene with a single object of interest, outperforming existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01978 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ROI-GS: Interest-based Local Quality 3D Gaussian Splatting Bui, Quoc-Anh Rougeron, Gilles Morin, Géraldine Gasparini, Simone Graphics Computer Vision and Pattern Recognition 68U05, 68T45 (Primary) 68T07, 68-04 (Secondary) I.2.10; I.3.3; I.3.5; I.3.7; I.4.5; I.4.6; I.4.8; I.4.10 We tackle the challenge of efficiently reconstructing 3D scenes with high detail on objects of interest. Existing 3D Gaussian Splatting (3DGS) methods allocate resources uniformly across the scene, limiting fine detail to Regions Of Interest (ROIs) and leading to inflated model size. We propose ROI-GS, an object-aware framework that enhances local details through object-guided camera selection, targeted Object training, and seamless integration of high-fidelity object of interest reconstructions into the global scene. Our method prioritizes higher resolution details on chosen objects while maintaining real-time performance. Experiments show that ROI-GS significantly improves local quality (up to 2.96 dB PSNR), while reducing overall model size by $\approx 17\%$ of baseline and achieving faster training for a scene with a single object of interest, outperforming existing methods. |
| title | ROI-GS: Interest-based Local Quality 3D Gaussian Splatting |
| topic | Graphics Computer Vision and Pattern Recognition 68U05, 68T45 (Primary) 68T07, 68-04 (Secondary) I.2.10; I.3.3; I.3.5; I.3.7; I.4.5; I.4.6; I.4.8; I.4.10 |
| url | https://arxiv.org/abs/2510.01978 |