{"ID":2871474,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.11453","arxiv_id":"2509.11453","title":"Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking","abstract":"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.","short_abstract":"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 occlude...","url_abs":"https://arxiv.org/abs/2509.11453","url_pdf":"https://arxiv.org/pdf/2509.11453v3","authors":"[\"BaiChen Fan\",\"Yuanxi Cui\",\"Jian Li\",\"Qin Wang\",\"Shibo Zhao\",\"Muqing Cao\",\"Sifan Zhou\"]","published":"2025-09-14T21:57:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.RO\"]","methods":"[]","has_code":false,"code_links":[{"ID":609862,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2871474,"paper_url":"https://arxiv.org/abs/2509.11453","paper_title":"Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking","repo_url":"https://github.com/FiBonaCci225/TrajTrack","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}