{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/large-displacement-3d-object-tracking-with","title":"Large-displacement 3D Object Tracking with Hybrid Non-local Optimization","arxiv_id":"2207.12620","date":"2022-07-26","proceeding":null,"authors":["Xuhui Tian","Xinran Lin","Fan Zhong","Xueying Qin"],"abstract":"Optimization-based 3D object tracking is known to be precise and fast, but sensitive to large inter-frame displacements. In this paper we propose a fast and effective non-local 3D tracking method. Based on the observation that erroneous local minimum are mostly due to the out-of-plane rotation, we propose a hybrid approach combining non-local and local optimizations for different parameters, resulting in efficient non-local search in the 6D pose space. In addition, a precomputed robust contour-based tracking method is proposed for the pose optimization. By using long search lines with multiple candidate correspondences, it can adapt to different frame displacements without the need of coarse-to-fine search. After the pre-computation, pose updates can be conducted very fast, enabling the non-local optimization to run in real time. Our method outperforms all previous methods for both small and large displacements. For large displacements, the accuracy is greatly improved ($81.7\\% \\;\\text{v.s.}\\; 19.4\\%$). At the same time, real-time speed ($>$50fps) can be achieved with only CPU. The source code is available at \\url{https://github.com/cvbubbles/nonlocal-3dtracking}.","url_abs":"https://arxiv.org/abs/2207.12620v1","url_pdf":"https://arxiv.org/pdf/2207.12620v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"large-displacement-3d-object-tracking-with","repo_url":"https://github.com/cvbubbles/nonlocal-3dtracking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-object-tracking","task_name":"3D Object Tracking"},{"task_slug":null,"task_name":"CPU"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.12620","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}