{"ID":2847240,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.00510","arxiv_id":"2511.00510","title":"OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback","abstract":"To address panoramic distortion, large search space, and identity ambiguity under a 360° FoV, OmniTrack++ adopts a feedback-driven framework that progressively refines perception with trajectory cues. A DynamicSSM block first stabilizes panoramic features, implicitly alleviating geometric distortion. On top of normalized representations, FlexiTrack Instances use trajectory-informed feedback for flexible localization and reliable short-term association. To ensure long-term robustness, an ExpertTrack Memory consolidates appearance cues via a Mixture-of-Experts design, enabling recovery from fragmented tracks and reducing identity drift. Finally, a Tracklet Management module adaptively switches between end-to-end and tracking-by-detection modes according to scene dynamics, offering a balanced and scalable solution for panoramic MOT. To support rigorous evaluation, we establish the EmboTrack benchmark, a comprehensive dataset for panoramic MOT that includes QuadTrack, captured with a quadruped robot, and BipTrack, collected with a bipedal wheel-legged robot. Together, these datasets span wide-angle environments and diverse motion patterns, providing a challenging testbed for real-world panoramic perception. Extensive experiments on JRDB and EmboTrack demonstrate that OmniTrack++ achieves state-of-the-art performance, yielding substantial HOTA improvements of +3.94 on JRDB and +15.03 on QuadTrack over the original OmniTrack. These results highlight the effectiveness of trajectory-informed feedback, adaptive paradigm switching, and robust long-term memory in advancing panoramic multi-object tracking. Datasets and code will be made available at https://github.com/xifen523/OmniTrack.","short_abstract":"To address panoramic distortion, large search space, and identity ambiguity under a 360° FoV, OmniTrack++ adopts a feedback-driven framework that progressively refines perception with trajectory cues. A DynamicSSM block first stabilizes panoramic features, implicitly alleviating geometric distortion. On top of normaliz...","url_abs":"https://arxiv.org/abs/2511.00510","url_pdf":"https://arxiv.org/pdf/2511.00510v2","authors":"[\"Kai Luo\",\"Hao Shi\",\"Kunyu Peng\",\"Fei Teng\",\"Sheng Wu\",\"Kaiwei Wang\",\"Kailun Yang\"]","published":"2025-11-01T11:28:05Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\",\"eess.IV\"]","methods":"[]","has_code":false,"code_links":[{"ID":607501,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2847240,"paper_url":"https://arxiv.org/abs/2511.00510","paper_title":"OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback","repo_url":"https://github.com/xifen523/OmniTrack","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}