Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908886644031488 |
|---|---|
| author | Fan, BaiChen Cui, Yuanxi Li, Jian Wang, Qin Zhao, Shibo Cao, Muqing Zhou, Sifan |
| author_facet | Fan, BaiChen Cui, Yuanxi Li, Jian Wang, Qin Zhao, Shibo Cao, Muqing Zhou, Sifan |
| contents | LiDAR-based 3D single object tracking (3D SOT) is a critical task in robotics and autonomous systems. Existing methods typically follow frame-wise motion estimation or a sequence-based paradigm. However, the two-frame methods are efficient but lack long-term temporal context, making them vulnerable in sparse or occluded scenes, while sequence-based methods that process multiple point clouds gain robustness at a significant computational cost. To resolve this dilemma, we propose a novel trajectory-based paradigm and its instantiation, TrajTrack. TrajTrack is a lightweight framework that enhances a base two-frame tracker by implicitly learning motion continuity from historical bounding box trajectories alone-without requiring additional, costly point cloud inputs. It first generates a fast, explicit motion proposal and then uses an implicit motion modeling module to predict the future trajectory, which in turn refines and corrects the initial proposal. Extensive experiments on the large-scale NuScenes benchmark show that TrajTrack achieves new state-of-the-art performance, dramatically improving tracking precision by 3.02% over a strong baseline while running at 55 FPS. Besides, we also demonstrate the strong generalizability of TrajTrack across different base trackers. Code is available at https://github.com/FiBonaCci225/TrajTrack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11453 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking Fan, BaiChen Cui, Yuanxi Li, Jian Wang, Qin Zhao, Shibo Cao, Muqing Zhou, Sifan Computer Vision and Pattern Recognition Artificial Intelligence Robotics LiDAR-based 3D single object tracking (3D SOT) is a critical task in robotics and autonomous systems. Existing methods typically follow frame-wise motion estimation or a sequence-based paradigm. However, the two-frame methods are efficient but lack long-term temporal context, making them vulnerable in sparse or occluded scenes, while sequence-based methods that process multiple point clouds gain robustness at a significant computational cost. To resolve this dilemma, we propose a novel trajectory-based paradigm and its instantiation, TrajTrack. TrajTrack is a lightweight framework that enhances a base two-frame tracker by implicitly learning motion continuity from historical bounding box trajectories alone-without requiring additional, costly point cloud inputs. It first generates a fast, explicit motion proposal and then uses an implicit motion modeling module to predict the future trajectory, which in turn refines and corrects the initial proposal. Extensive experiments on the large-scale NuScenes benchmark show that TrajTrack achieves new state-of-the-art performance, dramatically improving tracking precision by 3.02% over a strong baseline while running at 55 FPS. Besides, we also demonstrate the strong generalizability of TrajTrack across different base trackers. Code is available at https://github.com/FiBonaCci225/TrajTrack. |
| title | Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2509.11453 |