IRS: Instance-Level 3D Scene Graphs via Room Prior Guided LiDAR-Camera Fusion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912418805841920 |
|---|---|
| author | Chen, Hongming Lin, Yiyang Li, Ziliang Ye, Biyu Zhang, Yuying Lyu, Ximin |
| author_facet | Chen, Hongming Lin, Yiyang Li, Ziliang Ye, Biyu Zhang, Yuying Lyu, Ximin |
| contents | Indoor scene understanding remains a fundamental challenge in robotics, with direct implications for downstream tasks such as navigation and manipulation. Traditional approaches often rely on closed-set recognition or loop closure, limiting their adaptability in open-world environments. With the advent of visual foundation models (VFMs), open-vocabulary recognition and natural language querying have become feasible, unlocking new possibilities for 3D scene graph construction.
In this paper, we propose a robust and efficient framework for instance-level 3D scene graph construction via LiDAR-camera fusion. Leveraging LiDAR's wide field of view (FOV) and long-range sensing capabilities, we rapidly acquire room-level geometric priors. Multi-level VFMs are employed to improve the accuracy and consistency of semantic extraction. During instance fusion, room-based segmentation enables parallel processing, while the integration of geometric and semantic cues significantly enhances fusion accuracy and robustness. Compared to state-of-the-art methods, our approach achieves up to an order-of-magnitude improvement in construction speed while maintaining high semantic precision.
Extensive experiments in both simulated and real-world environments validate the effectiveness of our approach. We further demonstrate its practical value through a language-guided semantic navigation task, highlighting its potential for real-world robotic applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06804 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IRS: Instance-Level 3D Scene Graphs via Room Prior Guided LiDAR-Camera Fusion Chen, Hongming Lin, Yiyang Li, Ziliang Ye, Biyu Zhang, Yuying Lyu, Ximin Robotics Indoor scene understanding remains a fundamental challenge in robotics, with direct implications for downstream tasks such as navigation and manipulation. Traditional approaches often rely on closed-set recognition or loop closure, limiting their adaptability in open-world environments. With the advent of visual foundation models (VFMs), open-vocabulary recognition and natural language querying have become feasible, unlocking new possibilities for 3D scene graph construction. In this paper, we propose a robust and efficient framework for instance-level 3D scene graph construction via LiDAR-camera fusion. Leveraging LiDAR's wide field of view (FOV) and long-range sensing capabilities, we rapidly acquire room-level geometric priors. Multi-level VFMs are employed to improve the accuracy and consistency of semantic extraction. During instance fusion, room-based segmentation enables parallel processing, while the integration of geometric and semantic cues significantly enhances fusion accuracy and robustness. Compared to state-of-the-art methods, our approach achieves up to an order-of-magnitude improvement in construction speed while maintaining high semantic precision. Extensive experiments in both simulated and real-world environments validate the effectiveness of our approach. We further demonstrate its practical value through a language-guided semantic navigation task, highlighting its potential for real-world robotic applications. |
| title | IRS: Instance-Level 3D Scene Graphs via Room Prior Guided LiDAR-Camera Fusion |
| topic | Robotics |
| url | https://arxiv.org/abs/2506.06804 |