{"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/p2b-point-to-box-network-for-3d-object","title":"P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds","arxiv_id":"2005.13888","date":"2020-05-28","proceeding":"CVPR 2020 6","authors":["Haozhe Qi","Chen Feng","Zhiguo Cao","Feng Zhao","Yang Xiao"],"abstract":"Towards 3D object tracking in point clouds, a novel point-to-box network termed P2B is proposed in an end-to-end learning manner. Our main idea is to first localize potential target centers in 3D search area embedded with target information. Then point-driven 3D target proposal and verification are executed jointly. In this way, the time-consuming 3D exhaustive search can be avoided. Specifically, we first sample seeds from the point clouds in template and search area respectively. Then, we execute permutation-invariant feature augmentation to embed target clues from template into search area seeds and represent them with target-specific features. Consequently, the augmented search area seeds regress the potential target centers via Hough voting. The centers are further strengthened with seed-wise targetness scores. Finally, each center clusters its neighbors to leverage the ensemble power for joint 3D target proposal and verification. We apply PointNet++ as our backbone and experiments on KITTI tracking dataset demonstrate P2B's superiority (~10%'s improvement over state-of-the-art). Note that P2B can run with 40FPS on a single NVIDIA 1080Ti GPU. Our code and model are available at https://github.com/HaozheQi/P2B.","url_abs":"https://arxiv.org/abs/2005.13888v1","url_pdf":"https://arxiv.org/pdf/2005.13888v1.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":"p2b-point-to-box-network-for-3d-object","repo_url":"https://github.com/HaozheQi/P2B","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"p2b-point-to-box-network-for-3d-object","repo_url":"https://github.com/ghostish/open3dsot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-tracking","task_name":"3D Object Tracking"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2005.13888","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}