{"url":"/sota/edge-detection-on-mdbd","task":{"name":"Edge Detection","url":"/task/edge-detection","note":null},"dataset":{"name":"MDBD","url":"/dataset/mdbd"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Edge Detection** is a fundamental image processing technique which involves computing an image gradient to quantify the magnitude and direction of edges in an image. Image gradients are used in various downstream tasks in computer vision such as line detection, feature detection, and image classification.\r\n\r\n\r\n<span class=\"description-source\">Source: [Artistic Enhancement and Style Transfer of Image Edges using Directional Pseudo-coloring ](https://arxiv.org/abs/1906.07981)</span>\r\n\r\n( Image credit: [Kornia](https://github.com/kornia/kornia) )","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":["ODS","Number of parameters (M)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"ODS":null,"Number of parameters (M)":null}},"counts":{"rows":6,"rows_with_code":6,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DexiNed-a","metrics":{"ODS":"0.894"},"uses_additional_data":false,"paper_date":"2021-12-04","paper":"/paper/dense-extreme-inception-network-for-edge","paper_url":"https://arxiv.org/abs/2112.02250v2","paper_title":"Dense Extreme Inception Network for Edge Detection","code":"https://github.com/xavysp/DexiNed","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DexiNed-f","metrics":{"ODS":"0.891"},"uses_additional_data":false,"paper_date":"2021-12-04","paper":"/paper/dense-extreme-inception-network-for-edge","paper_url":"https://arxiv.org/abs/2112.02250v2","paper_title":"Dense Extreme Inception Network for Edge Detection","code":"https://github.com/xavysp/DexiNed","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CATS","metrics":{"ODS":"0.891"},"uses_additional_data":false,"paper_date":"2020-11-19","paper":"/paper/unmixing-convolutional-features-for-crisp","paper_url":"https://arxiv.org/abs/2011.09808v2","paper_title":"Unmixing Convolutional Features for Crisp Edge Detection","code":"https://github.com/WHUHLX/CATS","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"BDCN","metrics":{"ODS":"0.887"},"uses_additional_data":false,"paper_date":"2019-02-28","paper":"/paper/bi-directional-cascade-network-for-perceptual","paper_url":"http://arxiv.org/abs/1902.10903v1","paper_title":"Bi-Directional Cascade Network for Perceptual Edge Detection","code":"https://github.com/pkuCactus/BDCN","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"LDC","metrics":{"Number of parameters (M)":"674K","ODS":"0.880"},"uses_additional_data":false,"paper_date":"2022-06-27","paper":"/paper/ldc-lightweight-dense-cnn-for-edge-detection","paper_url":"https://ieeexplore.ieee.org/document/9807316","paper_title":"LDC: Lightweight Dense CNN for Edge Detection","code":"https://github.com/xavysp/LDC","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"RCF","metrics":{"ODS":"0.879"},"uses_additional_data":false,"paper_date":"2016-12-07","paper":"/paper/richer-convolutional-features-for-edge","paper_url":"https://arxiv.org/abs/1612.02103v3","paper_title":"Richer Convolutional Features for Edge Detection","code":"https://github.com/yun-liu/rcf","n_code_links":3,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":1,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0,"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"}}}