{"url":"/sota/visual-localization-on-oxford-radar-robotcar","task":{"name":"Visual Localization","url":"/task/visual-localization","note":null},"dataset":{"name":"Oxford Radar RobotCar (Full-6)","url":"/dataset/oxford-radar-robotcar-dataset"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Visual Localization** is the problem of estimating the camera pose of a given image relative to a visual representation of a known scene.\n\n\n<span class=\"description-source\">Source: [Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization ](https://arxiv.org/abs/1908.06387)</span>","description_from":"task","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":["Mean Translation Error"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean Translation Error":"lower"}},"counts":{"rows":16,"rows_with_code":16,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"LightLoc","metrics":{"Mean Translation Error":"2.67"},"uses_additional_data":false,"paper_date":"2025-03-22","paper":"/paper/lightloc-learning-outdoor-lidar-localization","paper_url":"https://arxiv.org/abs/2503.17814v1","paper_title":"LightLoc: Learning Outdoor LiDAR Localization at Light Speed","code":"https://github.com/liw95/lightloc","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"LISA","metrics":{"Mean Translation Error":"2.74"},"uses_additional_data":false,"paper_date":"2024-01-01","paper":"/paper/lisa-lidar-localization-with-semantic","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Yang_LiSA_LiDAR_Localization_with_Semantic_Awareness_CVPR_2024_paper.html","paper_title":"LiSA: LiDAR Localization with Semantic Awareness","code":"https://github.com/ybchun/lisa","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"SGLoc","metrics":{"Mean Translation Error":"3.14"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/sgloc-scene-geometry-encoding-for-outdoor","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Li_SGLoc_Scene_Geometry_Encoding_for_Outdoor_LiDAR_Localization_CVPR_2023_paper.html","paper_title":"SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization","code":"https://github.com/liw95/SGLoc","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"DiffLoc","metrics":{"Mean Translation Error":"3.53"},"uses_additional_data":false,"paper_date":"2024-01-01","paper":"/paper/diffloc-diffusion-model-for-outdoor-lidar","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Li_DiffLoc_Diffusion_Model_for_Outdoor_LiDAR_Localization_CVPR_2024_paper.html","paper_title":"DiffLoc: Diffusion Model for Outdoor LiDAR Localization","code":"https://github.com/liw95/diffloc","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"HypLiLoc","metrics":{"Mean Translation Error":"6.00"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/hypliloc-towards-effective-lidar-pose","paper_url":"https://arxiv.org/abs/2304.00932v2","paper_title":"HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion","code":"https://github.com/sijieaaa/hypliloc","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"PoseSOE","metrics":{"Mean Translation Error":"8.81"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/lidar-based-localization-using-universal","paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320322001662","paper_title":"LiDAR-based localization using universal encoding and memory-aware regression","code":"https://github.com/PSYZ1234/PosePN","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"PosePN++","metrics":{"Mean Translation Error":"10.64"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/lidar-based-localization-using-universal","paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320322001662","paper_title":"LiDAR-based localization using universal encoding and memory-aware regression","code":"https://github.com/PSYZ1234/PosePN","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"PoseMinkLoc","metrics":{"Mean Translation Error":"11.20"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/lidar-based-localization-using-universal","paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320322001662","paper_title":"LiDAR-based localization using universal encoding and memory-aware regression","code":"https://github.com/PSYZ1234/PosePN","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"MS-Transformer","metrics":{"Mean Translation Error":"11.69"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/learning-multi-scene-absolute-pose-regression","paper_url":"https://arxiv.org/abs/2103.11468v2","paper_title":"Learning Multi-Scene Absolute Pose Regression with Transformers","code":"https://github.com/yolish/multi-scene-pose-transformer","n_code_links":2,"syntology":{"n_ran":10,"n_unverified":10,"n_samples":20,"n_pointer_only_licence":20}},{"rank_in_archive_order":10,"model":"VMLoc","metrics":{"Mean Translation Error":"15.11"},"uses_additional_data":false,"paper_date":"2020-03-12","paper":"/paper/mvloc-multimodal-variational-geometry-aware","paper_url":"https://arxiv.org/abs/2003.07289v6","paper_title":"VMLoc: Variational Fusion For Learning-Based Multimodal Camera Localization","code":"https://github.com/kaichen-z/vmloc","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"PosePN","metrics":{"Mean Translation Error":"16.32"},"uses_additional_data":false,"paper_date":"2022-08-01","paper":"/paper/lidar-based-localization-using-universal","paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320322001662","paper_title":"LiDAR-based localization using universal encoding and memory-aware regression","code":"https://github.com/PSYZ1234/PosePN","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"AtLoc+","metrics":{"Mean Translation Error":"17.92"},"uses_additional_data":false,"paper_date":"2019-09-08","paper":"/paper/atloc-attention-guided-camera-localization","paper_url":"https://arxiv.org/abs/1909.03557v2","paper_title":"AtLoc: Attention Guided Camera Localization","code":"https://github.com/BingCS/AtLoc","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"AD-MapNet","metrics":{"Mean Translation Error":"18.43"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/prior-guided-dropout-for-robust-visual","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Huang_Prior_Guided_Dropout_for_Robust_Visual_Localization_in_Dynamic_Environments_ICCV_2019_paper.html","paper_title":"Prior Guided Dropout for Robust Visual Localization in Dynamic Environments","code":"https://github.com/zju3dv/RVL-Dynamic","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"DCP","metrics":{"Mean Translation Error":"18.45"},"uses_additional_data":false,"paper_date":"2019-05-08","paper":"/paper/190503304","paper_url":"https://arxiv.org/abs/1905.03304v1","paper_title":"Deep Closest Point: Learning Representations for Point Cloud Registration","code":"https://github.com/vinits5/learning3d","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":15,"model":"PointNetVLAD","metrics":{"Mean Translation Error":"28.48"},"uses_additional_data":false,"paper_date":"2018-04-10","paper":"/paper/pointnetvlad-deep-point-cloud-based-retrieval","paper_url":"http://arxiv.org/abs/1804.03492v3","paper_title":"PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition","code":"https://github.com/mikacuy/pointnetvlad","n_code_links":6,"syntology":null},{"rank_in_archive_order":16,"model":"MapNet","metrics":{"Mean Translation Error":"48.21"},"uses_additional_data":false,"paper_date":"2017-12-09","paper":"/paper/geometry-aware-learning-of-maps-for-camera","paper_url":"http://arxiv.org/abs/1712.03342v3","paper_title":"Geometry-Aware Learning of Maps for Camera Localization","code":"https://github.com/NVlabs/geomapnet","n_code_links":1,"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":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":13,"n_unverified":10,"n_samples":23,"n_pointer_only_licence":23,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":13,"n_unverified":10,"n_samples":23,"n_pointer_only_licence":23,"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"}}}