{"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/petr-position-embedding-transformation-for","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","arxiv_id":"2203.05625","date":"2022-03-10","proceeding":null,"authors":["Yingfei Liu","Tiancai Wang","Xiangyu Zhang","Jian Sun"],"abstract":"In this paper, we develop position embedding transformation (PETR) for multi-view 3D object detection. PETR encodes the position information of 3D coordinates into image features, producing the 3D position-aware features. Object query can perceive the 3D position-aware features and perform end-to-end object detection. PETR achieves state-of-the-art performance (50.4% NDS and 44.1% mAP) on standard nuScenes dataset and ranks 1st place on the benchmark. It can serve as a simple yet strong baseline for future research. Code is available at \\url{https://github.com/megvii-research/PETR}.","url_abs":"https://arxiv.org/abs/2203.05625v3","url_pdf":"https://arxiv.org/pdf/2203.05625v3.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":"petr-position-embedding-transformation-for","repo_url":"https://github.com/megvii-research/petr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"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":null,"task_name":"Position"},{"task_slug":"robust-camera-only-3d-object-detection","task_name":"Robust Camera Only 3D Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-3d-object-detection-on","task":"3D Object Detection","dataset":"3D Object Detection on Argoverse2 Camera Only","model":"PETR","rank_in_archive_order":3,"of":3,"metrics":{"Average mAP":"17.6"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-truckscenes","task":"3D Object Detection","dataset":"TruckScenes","model":"PETR","rank_in_archive_order":3,"of":4,"metrics":{"NDS":"12.1","mAP":"2.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.05625","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}