{"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/osp2b-one-stage-point-to-box-network-for-3d","title":"OSP2B: One-Stage Point-to-Box Network for 3D Siamese Tracking","arxiv_id":"2304.11584","date":"2023-04-23","proceeding":null,"authors":["Jiahao Nie","Zhiwei He","Yuxiang Yang","Zhengyi Bao","Mingyu Gao","Jing Zhang"],"abstract":"Two-stage point-to-box network acts as a critical role in the recent popular 3D Siamese tracking paradigm, which first generates proposals and then predicts corresponding proposal-wise scores. However, such a network suffers from tedious hyper-parameter tuning and task misalignment, limiting the tracking performance. Towards these concerns, we propose a simple yet effective one-stage point-to-box network for point cloud-based 3D single object tracking. It synchronizes 3D proposal generation and center-ness score prediction by a parallel predictor without tedious hyper-parameters. To guide a task-aligned score ranking of proposals, a center-aware focal loss is proposed to supervise the training of the center-ness branch, which enhances the network's discriminative ability to distinguish proposals of different quality. Besides, we design a binary target classifier to identify target-relevant points. By integrating the derived classification scores with the center-ness scores, the resulting network can effectively suppress interference proposals and further mitigate task misalignment. Finally, we present a novel one-stage Siamese tracker OSP2B equipped with the designed network. Extensive experiments on challenging benchmarks including KITTI and Waymo SOT Dataset show that our OSP2B achieves leading performance with a considerable real-time speed.Code will be available at https://github.com/haooozi/OSP2B.","url_abs":"https://arxiv.org/abs/2304.11584v2","url_pdf":"https://arxiv.org/pdf/2304.11584v2.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":"osp2b-one-stage-point-to-box-network-for-3d","repo_url":"https://github.com/haooozi/osp2b","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"osp2b-one-stage-point-to-box-network-for-3d","repo_url":"https://github.com/xmm-prio/bevtrack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-single-object-tracking","task_name":"3D Single Object Tracking"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[{"method_slug":"focal-loss","method_name":"Focal Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.11584","atlas_url":"https://app.syntology.ai/?focus=2304.11584","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}