{"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/detzero-rethinking-offboard-3d-object","title":"DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds","arxiv_id":"2306.06023","date":"2023-06-09","proceeding":"ICCV 2023 1","authors":["Tao Ma","Xuemeng Yang","Hongbin Zhou","Xin Li","Botian Shi","Junjie Liu","Yuchen Yang","Zhizheng Liu","Liang He","Yu Qiao","Yikang Li","Hongsheng Li"],"abstract":"Existing offboard 3D detectors always follow a modular pipeline design to take advantage of unlimited sequential point clouds. We have found that the full potential of offboard 3D detectors is not explored mainly due to two reasons: (1) the onboard multi-object tracker cannot generate sufficient complete object trajectories, and (2) the motion state of objects poses an inevitable challenge for the object-centric refining stage in leveraging the long-term temporal context representation. To tackle these problems, we propose a novel paradigm of offboard 3D object detection, named DetZero. Concretely, an offline tracker coupled with a multi-frame detector is proposed to focus on the completeness of generated object tracks. An attention-mechanism refining module is proposed to strengthen contextual information interaction across long-term sequential point clouds for object refining with decomposed regression methods. Extensive experiments on Waymo Open Dataset show our DetZero outperforms all state-of-the-art onboard and offboard 3D detection methods. Notably, DetZero ranks 1st place on Waymo 3D object detection leaderboard with 85.15 mAPH (L2) detection performance. Further experiments validate the application of taking the place of human labels with such high-quality results. Our empirical study leads to rethinking conventions and interesting findings that can guide future research on offboard 3D object detection.","url_abs":"https://arxiv.org/abs/2306.06023v2","url_pdf":"https://arxiv.org/pdf/2306.06023v2.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":"detzero-rethinking-offboard-3d-object","repo_url":"https://github.com/pjlab-adg/detzero","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-multi-object-tracking","task_name":"3D Multi-Object Tracking"},{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-multi-object-tracking-on-waymo-open","task":"3D Multi-Object Tracking","dataset":"Waymo Open Dataset","model":"DetZero","rank_in_archive_order":1,"of":3,"metrics":{"MOTA/L2":"0.7505"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.06023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06023"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pjlab-adg/detzero","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2a6dfff40d3e729b","entry":"gaussian_radius","repo":"pjlab-adg/detzero","repo_kind":"official","path":"detection/detzero_det/utils/centernet_utils.py","file_url":"https://github.com/pjlab-adg/detzero/blob/HEAD/detection/detzero_det/utils/centernet_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2a6dfff40d3e729b"}},{"code_sha256_prefix":"c2c12a52b4ec1abd","entry":"draw_gaussian_to_heatmap","repo":"pjlab-adg/detzero","repo_kind":"official","path":"detection/detzero_det/utils/centernet_utils.py","file_url":"https://github.com/pjlab-adg/detzero/blob/HEAD/detection/detzero_det/utils/centernet_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2c12a52b4ec1abd"}},{"code_sha256_prefix":"86282b7f90be63f2","entry":"gaussian2D","repo":"pjlab-adg/detzero","repo_kind":"official","path":"detection/detzero_det/utils/centernet_utils.py","file_url":"https://github.com/pjlab-adg/detzero/blob/HEAD/detection/detzero_det/utils/centernet_utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86282b7f90be63f2"}},{"code_sha256_prefix":"3f1ad379ea341f41","entry":"in_hull","repo":"pjlab-adg/detzero","repo_kind":"official","path":"utils/detzero_utils/box_utils.py","file_url":"https://github.com/pjlab-adg/detzero/blob/HEAD/utils/detzero_utils/box_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3f1ad379ea341f41"}},{"code_sha256_prefix":"8e622cb07954d501","entry":"load_params_with_optimizer","repo":"pjlab-adg/detzero","repo_kind":"official","path":"utils/detzero_utils/model_utils.py","file_url":"https://github.com/pjlab-adg/detzero/blob/HEAD/utils/detzero_utils/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e622cb07954d501"}},{"code_sha256_prefix":"230ce0b7330d1eab","entry":"make_fc_layers","repo":"pjlab-adg/detzero","repo_kind":"official","path":"utils/detzero_utils/model_utils.py","file_url":"https://github.com/pjlab-adg/detzero/blob/HEAD/utils/detzero_utils/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"230ce0b7330d1eab"}},{"code_sha256_prefix":"7231a044b5bbbac6","entry":"make_linear_layers","repo":"pjlab-adg/detzero","repo_kind":"official","path":"utils/detzero_utils/model_utils.py","file_url":"https://github.com/pjlab-adg/detzero/blob/HEAD/utils/detzero_utils/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7231a044b5bbbac6"}},{"code_sha256_prefix":"488b91d67a807558","entry":"neg_loss_cornernet","repo":"pjlab-adg/detzero","repo_kind":"official","path":"detection/detzero_det/utils/loss_utils.py","file_url":"https://github.com/pjlab-adg/detzero/blob/HEAD/detection/detzero_det/utils/loss_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"488b91d67a807558"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}