MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911056701423616 |
|---|---|
| author | Hu, Zhaofeng Zhou, Sifan Yuan, Zhihang Yang, Dawei Zhao, Shibo Liang, Ci-Jyun |
| author_facet | Hu, Zhaofeng Zhou, Sifan Yuan, Zhihang Yang, Dawei Zhao, Shibo Liang, Ci-Jyun |
| contents | 3D single object tracking is essential in autonomous driving and robotics. Existing methods often struggle with sparse and incomplete point cloud scenarios. To address these limitations, we propose a Multimodal-guided Virtual Cues Projection (MVCP) scheme that generates virtual cues to enrich sparse point clouds. Additionally, we introduce an enhanced tracker MVCTrack based on the generated virtual cues. Specifically, the MVCP scheme seamlessly integrates RGB sensors into LiDAR-based systems, leveraging a set of 2D detections to create dense 3D virtual cues that significantly improve the sparsity of point clouds. These virtual cues can naturally integrate with existing LiDAR-based 3D trackers, yielding substantial performance gains. Extensive experiments demonstrate that our method achieves competitive performance on the NuScenes dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02734 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues Hu, Zhaofeng Zhou, Sifan Yuan, Zhihang Yang, Dawei Zhao, Shibo Liang, Ci-Jyun Computer Vision and Pattern Recognition Robotics 3D single object tracking is essential in autonomous driving and robotics. Existing methods often struggle with sparse and incomplete point cloud scenarios. To address these limitations, we propose a Multimodal-guided Virtual Cues Projection (MVCP) scheme that generates virtual cues to enrich sparse point clouds. Additionally, we introduce an enhanced tracker MVCTrack based on the generated virtual cues. Specifically, the MVCP scheme seamlessly integrates RGB sensors into LiDAR-based systems, leveraging a set of 2D detections to create dense 3D virtual cues that significantly improve the sparsity of point clouds. These virtual cues can naturally integrate with existing LiDAR-based 3D trackers, yielding substantial performance gains. Extensive experiments demonstrate that our method achieves competitive performance on the NuScenes dataset. |
| title | MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2412.02734 |