{"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/polarformer-multi-camera-3d-object-detection","title":"PolarFormer: Multi-camera 3D Object Detection with Polar Transformer","arxiv_id":"2206.15398","date":"2022-06-30","proceeding":null,"authors":["Yanqin Jiang","Li Zhang","Zhenwei Miao","Xiatian Zhu","Jin Gao","Weiming Hu","Yu-Gang Jiang"],"abstract":"3D object detection in autonomous driving aims to reason \"what\" and \"where\" the objects of interest present in a 3D world. Following the conventional wisdom of previous 2D object detection, existing methods often adopt the canonical Cartesian coordinate system with perpendicular axis. However, we conjugate that this does not fit the nature of the ego car's perspective, as each onboard camera perceives the world in shape of wedge intrinsic to the imaging geometry with radical (non-perpendicular) axis. Hence, in this paper we advocate the exploitation of the Polar coordinate system and propose a new Polar Transformer (PolarFormer) for more accurate 3D object detection in the bird's-eye-view (BEV) taking as input only multi-camera 2D images. Specifically, we design a cross attention based Polar detection head without restriction to the shape of input structure to deal with irregular Polar grids. For tackling the unconstrained object scale variations along Polar's distance dimension, we further introduce a multi-scalePolar representation learning strategy. As a result, our model can make best use of the Polar representation rasterized via attending to the corresponding image observation in a sequence-to-sequence fashion subject to the geometric constraints. Thorough experiments on the nuScenes dataset demonstrate that our PolarFormer outperforms significantly state-of-the-art 3D object detection alternatives.","url_abs":"https://arxiv.org/abs/2206.15398v6","url_pdf":"https://arxiv.org/pdf/2206.15398v6.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":"polarformer-multi-camera-3d-object-detection","repo_url":"https://github.com/fudan-zvg/polarformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"2d-object-detection","task_name":"2D Object Detection"},{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"robust-camera-only-3d-object-detection","task_name":"Robust Camera Only 3D Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-nuscenes-camera-only","task":"3D Object Detection","dataset":"nuScenes Camera Only","model":"PolarFormer","rank_in_archive_order":17,"of":19,"metrics":{"Future Frame":"false","NDS":"57.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.15398","atlas_url":"https://app.syntology.ai/?focus=2206.15398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.15398"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/fudan-zvg/polarformer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"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":"c637c42a302bb63c","entry":"conv1x1","repo":"fudan-zvg/polarformer","repo_kind":"official","path":"projects/mmdet3d_plugin/models/backbones/vovnet.py","file_url":"https://github.com/fudan-zvg/polarformer/blob/HEAD/projects/mmdet3d_plugin/models/backbones/vovnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c637c42a302bb63c"}},{"code_sha256_prefix":"303f4d3695ad18f1","entry":"conv3x3","repo":"fudan-zvg/polarformer","repo_kind":"official","path":"projects/mmdet3d_plugin/models/backbones/vovnet.py","file_url":"https://github.com/fudan-zvg/polarformer/blob/HEAD/projects/mmdet3d_plugin/models/backbones/vovnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"303f4d3695ad18f1"}},{"code_sha256_prefix":"c12fa9dce0d5fd34","entry":"inverse_sigmoid","repo":"fudan-zvg/polarformer","repo_kind":"official","path":"projects/mmdet3d_plugin/models/utils/polar_transformer.py","file_url":"https://github.com/fudan-zvg/polarformer/blob/HEAD/projects/mmdet3d_plugin/models/utils/polar_transformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c12fa9dce0d5fd34"}},{"code_sha256_prefix":"f7a6c2f2d2956250","entry":"nchw_to_nlc","repo":"fudan-zvg/polarformer","repo_kind":"official","path":"projects/mmdet3d_plugin/models/utils/polar_transformer.py","file_url":"https://github.com/fudan-zvg/polarformer/blob/HEAD/projects/mmdet3d_plugin/models/utils/polar_transformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7a6c2f2d2956250"}},{"code_sha256_prefix":"dff153b73a73c71b","entry":"nlc_to_nchw","repo":"fudan-zvg/polarformer","repo_kind":"official","path":"projects/mmdet3d_plugin/models/utils/polar_transformer.py","file_url":"https://github.com/fudan-zvg/polarformer/blob/HEAD/projects/mmdet3d_plugin/models/utils/polar_transformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dff153b73a73c71b"}},{"code_sha256_prefix":"8fda704fb3d1af09","entry":"normalize_bbox","repo":"fudan-zvg/polarformer","repo_kind":"official","path":"projects/mmdet3d_plugin/core/bbox/util.py","file_url":"https://github.com/fudan-zvg/polarformer/blob/HEAD/projects/mmdet3d_plugin/core/bbox/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8fda704fb3d1af09"}},{"code_sha256_prefix":"24cccf792e409dc2","entry":"perspective","repo":"fudan-zvg/polarformer","repo_kind":"official","path":"projects/mmdet3d_plugin/models/necks/fpn_trans.py","file_url":"https://github.com/fudan-zvg/polarformer/blob/HEAD/projects/mmdet3d_plugin/models/necks/fpn_trans.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24cccf792e409dc2"}},{"code_sha256_prefix":"260147942f1a8eb1","entry":"denormalize_bbox","repo":"fudan-zvg/polarformer","repo_kind":"official","path":"projects/mmdet3d_plugin/core/bbox/util.py","file_url":"https://github.com/fudan-zvg/polarformer/blob/HEAD/projects/mmdet3d_plugin/core/bbox/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"260147942f1a8eb1"}},{"code_sha256_prefix":"5ebf15e6940f6710","entry":"dw_conv3x3","repo":"fudan-zvg/polarformer","repo_kind":"official","path":"projects/mmdet3d_plugin/models/backbones/vovnet.py","file_url":"https://github.com/fudan-zvg/polarformer/blob/HEAD/projects/mmdet3d_plugin/models/backbones/vovnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ebf15e6940f6710"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}