{"url":"/sota/bird-s-eye-view-semantic-segmentation-on","task":{"name":"Bird's-Eye View Semantic Segmentation","url":"/task/bird-s-eye-view-semantic-segmentation","note":null},"dataset":{"name":"nuScenes","url":"/dataset/nuscenes"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["IoU veh - 224x480 - Vis filter. - 100x100 at 0.5","IoU veh - 448x800 - Vis filter. - 100x100 at 0.5","IoU veh - 224x480 - No vis filter - 100x100 at 0.5","IoU veh - 448x800 - No vis filter - 100x100 at 0.5","IoU ped - 224x480 - Vis filter. - 100x100 at 0.5","IoU lane - 224x480 - 100x100 at 0.5","IoU veh - 224x480 - No vis filter - 100x50 at 0.25","IoU vehicle - Setting 3"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"IoU veh - 224x480 - Vis filter. - 100x100 at 0.5":"higher","IoU veh - 448x800 - Vis filter. - 100x100 at 0.5":"higher","IoU veh - 224x480 - No vis filter - 100x100 at 0.5":"higher","IoU veh - 448x800 - No vis filter - 100x100 at 0.5":"higher","IoU ped - 224x480 - Vis filter. - 100x100 at 0.5":"higher","IoU lane - 224x480 - 100x100 at 0.5":"higher","IoU veh - 224x480 - No vis filter - 100x50 at 0.25":"higher","IoU vehicle - Setting 3":"higher"}},"counts":{"rows":17,"rows_with_code":12,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PointBeV","metrics":{"IoU ped - 224x480 - Vis filter. - 100x100 at 0.5":"19.9","IoU veh - 224x480 - No vis filter - 100x100 at 0.5":"39.9","IoU veh - 224x480 - Vis filter. - 100x100 at 0.5":"44.7","IoU veh - 448x800 - No vis filter - 100x100 at 0.5":"43.2","IoU veh - 448x800 - Vis filter. - 100x100 at 0.5":"48.7"},"uses_additional_data":false,"paper_date":"2023-12-01","paper":"/paper/pointbev-a-sparse-approach-to-bev-predictions","paper_url":"https://arxiv.org/abs/2312.00703v2","paper_title":"PointBeV: A Sparse Approach to BeV Predictions","code":"https://github.com/valeoai/pointbev","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"PointBeV (static)","metrics":{"IoU lane - 224x480 - 100x100 at 0.5":"49.6","IoU ped - 224x480 - Vis filter. - 100x100 at 0.5":"18.5","IoU veh - 224x480 - No vis filter - 100x100 at 0.5":"38.7","IoU veh - 224x480 - Vis filter. - 100x100 at 0.5":"44.0","IoU veh - 448x800 - No vis filter - 100x100 at 0.5":"42.1","IoU veh - 448x800 - Vis filter. - 100x100 at 0.5":"47.6"},"uses_additional_data":false,"paper_date":"2023-12-01","paper":"/paper/pointbev-a-sparse-approach-to-bev-predictions","paper_url":"https://arxiv.org/abs/2312.00703v2","paper_title":"PointBeV: A Sparse Approach to BeV Predictions","code":"https://github.com/valeoai/pointbev","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"Simple-BEV","metrics":{"IoU veh - 224x480 - No vis filter - 100x100 at 0.5":"36.9","IoU veh - 224x480 - Vis filter. - 100x100 at 0.5":"43.0","IoU veh - 448x800 - No vis filter - 100x100 at 0.5":"40.9","IoU veh - 448x800 - Vis filter. - 100x100 at 0.5":"46.6"},"uses_additional_data":false,"paper_date":"2022-06-16","paper":"/paper/a-simple-baseline-for-bev-perception-without","paper_url":"https://arxiv.org/abs/2206.07959v2","paper_title":"Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?","code":"https://github.com/valeoai/pointbev","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"BEVFormer","metrics":{"IoU lane - 224x480 - 100x100 at 0.5":"25.7","IoU veh - 224x480 - No vis filter - 100x100 at 0.5":"35.8","IoU veh - 224x480 - Vis filter. - 100x100 at 0.5":"42.0","IoU veh - 448x800 - No vis filter - 100x100 at 0.5":"39.0","IoU veh - 448x800 - Vis filter. - 100x100 at 0.5":"45.5"},"uses_additional_data":false,"paper_date":"2022-03-31","paper":"/paper/bevformer-learning-bird-s-eye-view","paper_url":"https://arxiv.org/abs/2203.17270v2","paper_title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","code":"https://github.com/fundamentalvision/BEVFormer","n_code_links":3,"syntology":null},{"rank_in_archive_order":5,"model":"FIERY (static)","metrics":{"IoU ped - 224x480 - Vis filter. - 100x100 at 0.5":"17.2","IoU veh - 224x480 - No vis filter - 100x100 at 0.5":"35.8","IoU veh - 224x480 - Vis filter. - 100x100 at 0.5":"39.8"},"uses_additional_data":false,"paper_date":"2021-04-21","paper":"/paper/fiery-future-instance-prediction-in-bird-s","paper_url":"https://arxiv.org/abs/2104.10490v3","paper_title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","code":"https://github.com/wayveai/fiery","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"BAEFormer","metrics":{"IoU veh - 224x480 - No vis filter - 100x100 at 0.5":"36","IoU veh - 224x480 - Vis filter. - 100x100 at 0.5":"38.9","IoU veh - 448x800 - No vis filter - 100x100 at 0.5":"37.8","IoU veh - 448x800 - Vis filter. - 100x100 at 0.5":"41.0"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/baeformer-bi-directional-and-early","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Pan_BAEFormer_Bi-Directional_and_Early_Interaction_Transformers_for_Birds_Eye_View_CVPR_2023_paper.html","paper_title":"BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"LaRa","metrics":{"IoU veh - 224x480 - No vis filter - 100x100 at 0.5":"35.4","IoU veh - 224x480 - Vis filter. - 100x100 at 0.5":"38.9"},"uses_additional_data":false,"paper_date":"2022-06-27","paper":"/paper/lara-latents-and-rays-for-multi-camera-bird-s","paper_url":"https://arxiv.org/abs/2206.13294v2","paper_title":"LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation","code":"https://github.com/valeoai/LaRa","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"CVT","metrics":{"IoU veh - 224x480 - No vis filter - 100x100 at 0.5":"31.4","IoU veh - 224x480 - Vis filter. - 100x100 at 0.5":"36.0","IoU veh - 448x800 - No vis filter - 100x100 at 0.5":"32.5","IoU veh - 448x800 - Vis filter. - 100x100 at 0.5":"37.7"},"uses_additional_data":false,"paper_date":"2022-05-05","paper":"/paper/cross-view-transformers-for-real-time-map","paper_url":"https://arxiv.org/abs/2205.02833v1","paper_title":"Cross-view Transformers for real-time Map-view Semantic Segmentation","code":"https://github.com/bradyz/cross_view_transformers","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"FIERY","metrics":{"IoU veh - 224x480 - No vis filter - 100x100 at 0.5":"38.2","IoU veh - 224x480 - No vis filter - 100x50 at 0.25":"41.1","IoU vehicle - Setting 3":"58.5"},"uses_additional_data":false,"paper_date":"2021-04-21","paper":"/paper/fiery-future-instance-prediction-in-bird-s","paper_url":"https://arxiv.org/abs/2104.10490v3","paper_title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","code":"https://github.com/wayveai/fiery","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"TBP-Former","metrics":{"IoU ped - 224x480 - Vis filter. - 100x100 at 0.5":"18.6"},"uses_additional_data":false,"paper_date":"2023-03-17","paper":"/paper/tbp-former-learning-temporal-bird-s-eye-view","paper_url":"https://arxiv.org/abs/2303.09998v2","paper_title":"TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"TBP-Former (static)","metrics":{"IoU ped - 224x480 - Vis filter. - 100x100 at 0.5":"17.2"},"uses_additional_data":false,"paper_date":"2023-03-17","paper":"/paper/tbp-former-learning-temporal-bird-s-eye-view","paper_url":"https://arxiv.org/abs/2303.09998v2","paper_title":"TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Lift-Splat-Shoot","metrics":{"IoU ped - 224x480 - Vis filter. - 100x100 at 0.5":"15.0"},"uses_additional_data":false,"paper_date":"2020-08-13","paper":"/paper/lift-splat-shoot-encoding-images-from","paper_url":"https://arxiv.org/abs/2008.05711v1","paper_title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","code":"https://github.com/nv-tlabs/lift-splat-shoot","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"ST-P3","metrics":{"IoU ped - 224x480 - Vis filter. - 100x100 at 0.5":"14.5"},"uses_additional_data":false,"paper_date":"2022-07-15","paper":"/paper/st-p3-end-to-end-vision-based-autonomous","paper_url":"https://arxiv.org/abs/2207.07601v2","paper_title":"ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning","code":"https://github.com/opendrivelab/st-p3","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"PETRv2","metrics":{"IoU lane - 224x480 - 100x100 at 0.5":"44.8"},"uses_additional_data":false,"paper_date":"2022-06-02","paper":"/paper/petrv2-a-unified-framework-for-3d-perception","paper_url":"https://arxiv.org/abs/2206.01256v3","paper_title":"PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images","code":"https://github.com/megvii-research/petr","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"MatrixVT","metrics":{"IoU lane - 224x480 - 100x100 at 0.5":"44.8"},"uses_additional_data":false,"paper_date":"2022-11-19","paper":"/paper/matrixvt-efficient-multi-camera-to-bev","paper_url":"https://arxiv.org/abs/2211.10593v1","paper_title":"MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception","code":"https://github.com/megvii-basedetection/bevdepth","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"M^2BEV","metrics":{"IoU lane - 224x480 - 100x100 at 0.5":"38.0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"VED","metrics":{"IoU veh - 224x480 - No vis filter - 100x50 at 0.25":"8.8"},"uses_additional_data":false,"paper_date":"2018-04-06","paper":"/paper/monocular-semantic-occupancy-grid-mapping","paper_url":"http://arxiv.org/abs/1804.02176v3","paper_title":"Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":5,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":4,"n_unverified":11,"n_samples":15,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":4,"n_unverified":12,"n_samples":16,"n_pointer_only_licence":1,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}