FSHNet: Fully Sparse Hybrid Network for 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_ | 1866916778195550208 |
|---|---|
| author | Liu, Shuai Cui, Mingyue Li, Boyang Liang, Quanmin Hong, Tinghe Huang, Kai Shan, Yunxiao Huang, Kai |
| author_facet | Liu, Shuai Cui, Mingyue Li, Boyang Liang, Quanmin Hong, Tinghe Huang, Kai Shan, Yunxiao Huang, Kai |
| contents | Fully sparse 3D detectors have recently gained significant attention due to their efficiency in long-range detection. However, sparse 3D detectors extract features only from non-empty voxels, which impairs long-range interactions and causes the center feature missing. The former weakens the feature extraction capability, while the latter hinders network optimization. To address these challenges, we introduce the Fully Sparse Hybrid Network (FSHNet). FSHNet incorporates a proposed SlotFormer block to enhance the long-range feature extraction capability of existing sparse encoders. The SlotFormer divides sparse voxels using a slot partition approach, which, compared to traditional window partition, provides a larger receptive field. Additionally, we propose a dynamic sparse label assignment strategy to deeply optimize the network by providing more high-quality positive samples. To further enhance performance, we introduce a sparse upsampling module to refine downsampled voxels, preserving fine-grained details crucial for detecting small objects. Extensive experiments on the Waymo, nuScenes, and Argoverse2 benchmarks demonstrate the effectiveness of FSHNet. The code is available at https://github.com/Say2L/FSHNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03714 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FSHNet: Fully Sparse Hybrid Network for 3D Object Detection Liu, Shuai Cui, Mingyue Li, Boyang Liang, Quanmin Hong, Tinghe Huang, Kai Shan, Yunxiao Huang, Kai Computer Vision and Pattern Recognition Fully sparse 3D detectors have recently gained significant attention due to their efficiency in long-range detection. However, sparse 3D detectors extract features only from non-empty voxels, which impairs long-range interactions and causes the center feature missing. The former weakens the feature extraction capability, while the latter hinders network optimization. To address these challenges, we introduce the Fully Sparse Hybrid Network (FSHNet). FSHNet incorporates a proposed SlotFormer block to enhance the long-range feature extraction capability of existing sparse encoders. The SlotFormer divides sparse voxels using a slot partition approach, which, compared to traditional window partition, provides a larger receptive field. Additionally, we propose a dynamic sparse label assignment strategy to deeply optimize the network by providing more high-quality positive samples. To further enhance performance, we introduce a sparse upsampling module to refine downsampled voxels, preserving fine-grained details crucial for detecting small objects. Extensive experiments on the Waymo, nuScenes, and Argoverse2 benchmarks demonstrate the effectiveness of FSHNet. The code is available at https://github.com/Say2L/FSHNet. |
| title | FSHNet: Fully Sparse Hybrid Network for 3D Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.03714 |