Enhancing LiDAR Point Features with Foundation Model Priors for 3D Object Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912492617203712 |
|---|---|
| author | Mo, Yujian Wu, Yan Zhao, Junqiao Wang, Jijun Hu, Yinghao Yan, Jun |
| author_facet | Mo, Yujian Wu, Yan Zhao, Junqiao Wang, Jijun Hu, Yinghao Yan, Jun |
| contents | Recent advances in foundation models have opened up new possibilities for enhancing 3D perception. In particular, DepthAnything offers dense and reliable geometric priors from monocular RGB images, which can complement sparse LiDAR data in autonomous driving scenarios. However, such priors remain underutilized in LiDAR-based 3D object detection. In this paper, we address the limited expressiveness of raw LiDAR point features, especially the weak discriminative capability of the reflectance attribute, by introducing depth priors predicted by DepthAnything. These priors are fused with the original LiDAR attributes to enrich each point's representation. To leverage the enhanced point features, we propose a point-wise feature extraction module. Then, a Dual-Path RoI feature extraction framework is employed, comprising a voxel-based branch for global semantic context and a point-based branch for fine-grained structural details. To effectively integrate the complementary RoI features, we introduce a bidirectional gated RoI feature fusion module that balances global and local cues. Extensive experiments on the KITTI benchmark show that our method consistently improves detection accuracy, demonstrating the value of incorporating visual foundation model priors into LiDAR-based 3D object detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_13899 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing LiDAR Point Features with Foundation Model Priors for 3D Object Detection Mo, Yujian Wu, Yan Zhao, Junqiao Wang, Jijun Hu, Yinghao Yan, Jun Computer Vision and Pattern Recognition Recent advances in foundation models have opened up new possibilities for enhancing 3D perception. In particular, DepthAnything offers dense and reliable geometric priors from monocular RGB images, which can complement sparse LiDAR data in autonomous driving scenarios. However, such priors remain underutilized in LiDAR-based 3D object detection. In this paper, we address the limited expressiveness of raw LiDAR point features, especially the weak discriminative capability of the reflectance attribute, by introducing depth priors predicted by DepthAnything. These priors are fused with the original LiDAR attributes to enrich each point's representation. To leverage the enhanced point features, we propose a point-wise feature extraction module. Then, a Dual-Path RoI feature extraction framework is employed, comprising a voxel-based branch for global semantic context and a point-based branch for fine-grained structural details. To effectively integrate the complementary RoI features, we introduce a bidirectional gated RoI feature fusion module that balances global and local cues. Extensive experiments on the KITTI benchmark show that our method consistently improves detection accuracy, demonstrating the value of incorporating visual foundation model priors into LiDAR-based 3D object detection. |
| title | Enhancing LiDAR Point Features with Foundation Model Priors for 3D Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.13899 |