Learning Class Prototypes for Unified Sparse Supervised 3D Object Detection
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_ | 1866912428032262144 |
|---|---|
| author | Zhu, Yun Hui, Le Yang, Hang Qian, Jianjun Xie, Jin Yang, Jian |
| author_facet | Zhu, Yun Hui, Le Yang, Hang Qian, Jianjun Xie, Jin Yang, Jian |
| contents | Both indoor and outdoor scene perceptions are essential for embodied intelligence. However, current sparse supervised 3D object detection methods focus solely on outdoor scenes without considering indoor settings. To this end, we propose a unified sparse supervised 3D object detection method for both indoor and outdoor scenes through learning class prototypes to effectively utilize unlabeled objects. Specifically, we first propose a prototype-based object mining module that converts the unlabeled object mining into a matching problem between class prototypes and unlabeled features. By using optimal transport matching results, we assign prototype labels to high-confidence features, thereby achieving the mining of unlabeled objects. We then present a multi-label cooperative refinement module to effectively recover missed detections through pseudo label quality control and prototype label cooperation. Experiments show that our method achieves state-of-the-art performance under the one object per scene sparse supervised setting across indoor and outdoor datasets. With only one labeled object per scene, our method achieves about 78%, 90%, and 96% performance compared to the fully supervised detector on ScanNet V2, SUN RGB-D, and KITTI, respectively, highlighting the scalability of our method. Code is available at https://github.com/zyrant/CPDet3D. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21099 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Class Prototypes for Unified Sparse Supervised 3D Object Detection Zhu, Yun Hui, Le Yang, Hang Qian, Jianjun Xie, Jin Yang, Jian Computer Vision and Pattern Recognition Both indoor and outdoor scene perceptions are essential for embodied intelligence. However, current sparse supervised 3D object detection methods focus solely on outdoor scenes without considering indoor settings. To this end, we propose a unified sparse supervised 3D object detection method for both indoor and outdoor scenes through learning class prototypes to effectively utilize unlabeled objects. Specifically, we first propose a prototype-based object mining module that converts the unlabeled object mining into a matching problem between class prototypes and unlabeled features. By using optimal transport matching results, we assign prototype labels to high-confidence features, thereby achieving the mining of unlabeled objects. We then present a multi-label cooperative refinement module to effectively recover missed detections through pseudo label quality control and prototype label cooperation. Experiments show that our method achieves state-of-the-art performance under the one object per scene sparse supervised setting across indoor and outdoor datasets. With only one labeled object per scene, our method achieves about 78%, 90%, and 96% performance compared to the fully supervised detector on ScanNet V2, SUN RGB-D, and KITTI, respectively, highlighting the scalability of our method. Code is available at https://github.com/zyrant/CPDet3D. |
| title | Learning Class Prototypes for Unified Sparse Supervised 3D Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.21099 |