{"url":"/task/edge-detection","name":"Edge Detection","slug":"edge-detection","description_markdown":"**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) )","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":490,"papers_with_code":147,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":9,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/edge-detection-on-biped-1","slug":"edge-detection-on-biped-1","dataset":"BIPED","dataset_url":"/dataset/biped","rows_in_archive":6,"metrics":["ODS","Number of parameters (M)"],"first_row_in_archive_order":{"model":"DDN","paper_title":"A Doubly Decoupled Network for edge detection","paper_url":"/paper/a-doubly-decoupled-network-for-edge-detection","paper_date":"2025-04-01","arxiv_id":null,"code_links":[{"title":"Li-yachuan/DDN","url":"https://github.com/Li-yachuan/DDN"}],"syntology":null}},{"leaderboard":"/sota/edge-detection-on-mdbd","slug":"edge-detection-on-mdbd","dataset":"MDBD","dataset_url":"/dataset/mdbd","rows_in_archive":6,"metrics":["ODS","Number of parameters (M)"],"first_row_in_archive_order":{"model":"DexiNed-a","paper_title":"Dense Extreme Inception Network for Edge Detection","paper_url":"/paper/dense-extreme-inception-network-for-edge","paper_date":"2021-12-04","arxiv_id":"2112.02250","code_links":[{"title":"xavysp/DexiNed","url":"https://github.com/xavysp/DexiNed"}],"syntology":null}},{"leaderboard":"/sota/edge-detection-on-uded","slug":"edge-detection-on-uded","dataset":"UDED","dataset_url":"/dataset/uded","rows_in_archive":5,"metrics":["ODS"],"first_row_in_archive_order":{"model":"DDN","paper_title":"A Doubly Decoupled Network for edge detection","paper_url":"/paper/a-doubly-decoupled-network-for-edge-detection","paper_date":"2025-04-01","arxiv_id":null,"code_links":[{"title":"Li-yachuan/DDN","url":"https://github.com/Li-yachuan/DDN"}],"syntology":null}},{"leaderboard":"/sota/edge-detection-on-brind","slug":"edge-detection-on-brind","dataset":"BRIND","dataset_url":"/dataset/brind","rows_in_archive":3,"metrics":["ODS","Number of parameters (M)"],"first_row_in_archive_order":{"model":"LDC","paper_title":"LDC: Lightweight Dense CNN for Edge Detection","paper_url":"/paper/ldc-lightweight-dense-cnn-for-edge-detection","paper_date":"2022-06-27","arxiv_id":null,"code_links":[{"title":"xavysp/LDC","url":"https://github.com/xavysp/LDC"}],"syntology":null}},{"leaderboard":"/sota/edge-detection-on-cid","slug":"edge-detection-on-cid","dataset":"CID","dataset_url":"/dataset/cid","rows_in_archive":2,"metrics":["ODS"],"first_row_in_archive_order":{"model":"DexiNed (WACV'2020)","paper_title":"Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection","paper_url":"/paper/dense-extreme-inception-network-towards-a","paper_date":"2019-09-04","arxiv_id":"1909.01955","code_links":[{"title":"xavysp/DexiNed","url":"https://github.com/xavysp/DexiNed"},{"title":"a-nau/Plane-Segmentation-Refinement","url":"https://github.com/a-nau/Plane-Segmentation-Refinement"},{"title":"xavysp/MBIPED","url":"https://github.com/xavysp/MBIPED"},{"title":"chaitravi-ce/Edge-Detection-Using-ML","url":"https://github.com/chaitravi-ce/Edge-Detection-Using-ML"}],"syntology":{"n":19,"n_ran":1,"n_unverified":18,"n_pointer_only":0}}},{"leaderboard":"/sota/edge-detection-on-cityscapes","slug":"edge-detection-on-cityscapes","dataset":"Cityscapes test","dataset_url":"/dataset/cityscapes","rows_in_archive":2,"metrics":["AP","Maximum F-measure"],"first_row_in_archive_order":{"model":"RPCNet","paper_title":"Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts","paper_url":"/paper/joint-semantic-segmentation-and-boundary","paper_date":"2020-04-16","arxiv_id":"2004.07684","code_links":[],"syntology":null}},{"leaderboard":"/sota/edge-detection-on-sbd","slug":"edge-detection-on-sbd","dataset":"SBD","dataset_url":"/dataset/sbd","rows_in_archive":2,"metrics":["Maximum F-measure"],"first_row_in_archive_order":{"model":"CASENet","paper_title":"CASENet: Deep Category-Aware Semantic Edge Detection","paper_url":"/paper/casenet-deep-category-aware-semantic-edge","paper_date":"2017-05-27","arxiv_id":"1705.09759","code_links":[{"title":"Lavender105/DFF","url":"https://github.com/Lavender105/DFF"},{"title":"Chrisding/seal","url":"https://github.com/Chrisding/seal"},{"title":"anirudh-chakravarthy/CASENet","url":"https://github.com/anirudh-chakravarthy/CASENet"},{"title":"milongo/CASENet","url":"https://github.com/milongo/CASENet"},{"title":"lijiaman/CASENet","url":"https://github.com/lijiaman/CASENet"},{"title":"Chrisding/sbd-preprocess","url":"https://github.com/Chrisding/sbd-preprocess"},{"title":"Chrisding/cityscapes-preprocess","url":"https://github.com/Chrisding/cityscapes-preprocess"},{"title":"arsenal9971/shearlet_semantic_edge","url":"https://github.com/arsenal9971/shearlet_semantic_edge"},{"title":"zhusiling/SEAL","url":"https://github.com/zhusiling/SEAL"},{"title":"yhcool14/cityscapes-preprocess","url":"https://github.com/yhcool14/cityscapes-preprocess"},{"title":"yhcool14/sbd-preprocess","url":"https://github.com/yhcool14/sbd-preprocess"}],"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":4}}},{"leaderboard":"/sota/edge-detection-on-bsds500-1","slug":"edge-detection-on-bsds500-1","dataset":"BSDS500","dataset_url":"/dataset/bsds500","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"RCN","paper_title":"Object Contour and Edge Detection with RefineContourNet","paper_url":"/paper/object-contour-and-edge-detection-with","paper_date":"2019-04-30","arxiv_id":"1904.13353","code_links":[{"title":"AndreKelm/RefineContourNet","url":"https://github.com/AndreKelm/RefineContourNet"},{"title":"daovietanhuet/ContourDetection","url":"https://github.com/daovietanhuet/ContourDetection"}],"syntology":null}}],"datasets":[{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":"","num_papers_in_archive":3702},{"url":"/dataset/bsds500","name":"BSDS500","full_name":"Berkeley Segmentation Dataset 500","num_papers_in_archive":261},{"url":"/dataset/sbd","name":"SBD","full_name":"Semantic Boundaries Dataset","num_papers_in_archive":147},{"url":"/dataset/biped","name":"BIPED","full_name":"Barcelona Images for Perceptual Edge Detection","num_papers_in_archive":25},{"url":"/dataset/uded","name":"UDED","full_name":"Unified Dataset for Edge Detection","num_papers_in_archive":8},{"url":"/dataset/mdbd","name":"MDBD","full_name":"Multicue Dataset for Edge Detection","num_papers_in_archive":6},{"url":"/dataset/brind","name":"BRIND","full_name":"BSDS-RIND","num_papers_in_archive":3},{"url":"/dataset/cid","name":"CID","full_name":"Campus Image Dataset","num_papers_in_archive":2},{"url":"/dataset/inria-horse","name":"INRIA-Horse","full_name":"INRIA-Horse","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/2d-object-detection","name":"2D Object Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":147,"tagged_in_all":490,"items":[{"url":"/paper/holistically-nested-edge-detection","title":"Holistically-Nested Edge Detection","date":"2015-04-24","arxiv_id":"1504.06375","repositories_listed":17,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/casenet-deep-category-aware-semantic-edge","title":"CASENet: Deep Category-Aware Semantic Edge Detection","date":"2017-05-27","arxiv_id":"1705.09759","repositories_listed":11,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/hed-unet-combined-segmentation-and-edge","title":"HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline","date":"2021-03-02","arxiv_id":"2103.01849","repositories_listed":5,"syntology":null},{"url":"/paper/kornia-an-open-source-differentiable-computer","title":"Kornia: an Open Source Differentiable Computer Vision Library for PyTorch","date":"2019-10-05","arxiv_id":"1910.02190","repositories_listed":5,"syntology":{"n":20,"n_ran":0,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/sanity-checks-for-saliency-maps","title":"Sanity Checks for Saliency Maps","date":"2018-10-08","arxiv_id":"1810.03292","repositories_listed":5,"syntology":null},{"url":"/paper/dense-extreme-inception-network-towards-a","title":"Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection","date":"2019-09-04","arxiv_id":"1909.01955","repositories_listed":4,"syntology":{"n":19,"n_ran":1,"n_unverified":18,"n_pointer_only":0}},{"url":"/paper/multimodal-generative-models-for-scalable","title":"Multimodal Generative Models for Scalable Weakly-Supervised Learning","date":"2018-02-14","arxiv_id":"1802.05335","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/simultaneous-edge-alignment-and-learning","title":"Simultaneous Edge Alignment and Learning","date":"2018-08-06","arxiv_id":"1808.01992","repositories_listed":3,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/richer-convolutional-features-for-edge","title":"Richer Convolutional Features for Edge Detection","date":"2016-12-07","arxiv_id":"1612.02103","repositories_listed":3,"syntology":null},{"url":"/paper/object-contour-detection-with-a-fully","title":"Object Contour Detection with a Fully Convolutional Encoder-Decoder Network","date":"2016-03-15","arxiv_id":"1603.04530","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/fast-detection-of-curved-edges-at-low-snr","title":"Fast Detection of Curved Edges at Low SNR","date":"2015-05-25","arxiv_id":"1505.06600","repositories_listed":3,"syntology":null},{"url":"/paper/leveraging-edge-detection-and-neural-networks","title":"Leveraging edge detection and neural networks for better UAV localization","date":"2024-04-09","arxiv_id":"2404.06207","repositories_listed":2,"syntology":null},{"url":"/paper/meganet-multi-scale-edge-guided-attention","title":"MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation","date":"2023-09-06","arxiv_id":"2309.03329","repositories_listed":2,"syntology":null},{"url":"/paper/decoupled-diffusion-models-with-explicit","title":"Simultaneous Image-to-Zero and Zero-to-Noise: Diffusion Models with Analytical Image Attenuation","date":"2023-06-23","arxiv_id":"2306.13720","repositories_listed":2,"syntology":null},{"url":"/paper/image-label-based-semantic-segmentation","title":"SILOP: An Automated Framework for Semantic Segmentation Using Image Labels Based on Object Perimeters","date":"2023-03-14","arxiv_id":"2303.07892","repositories_listed":2,"syntology":null},{"url":"/paper/pixel-difference-networks-for-efficient-edge","title":"Pixel Difference Networks for Efficient Edge Detection","date":"2021-08-16","arxiv_id":"2108.07009","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/a-novel-centroid-update-approach-for","title":"A novel centroid update approach for clustering-based superpixel methods and superpixel-based edge detection","date":"2019-10-18","arxiv_id":"1910.08439","repositories_listed":2,"syntology":null},{"url":"/paper/edge-direct-visual-odometry","title":"Edge-Direct Visual Odometry","date":"2019-06-11","arxiv_id":"1906.04838","repositories_listed":2,"syntology":null},{"url":"/paper/object-contour-and-edge-detection-with","title":"Object Contour and Edge Detection with RefineContourNet","date":"2019-04-30","arxiv_id":"1904.13353","repositories_listed":2,"syntology":null},{"url":"/paper/bi-directional-cascade-network-for-perceptual","title":"Bi-Directional Cascade Network for Perceptual Edge Detection","date":"2019-02-28","arxiv_id":"1902.10903","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/deepflux-for-skeletons-in-the-wild","title":"DeepFlux for Skeletons in the Wild","date":"2018-11-30","arxiv_id":"1811.12608","repositories_listed":2,"syntology":null},{"url":"/paper/faster-training-of-mask-r-cnn-by-focusing-on","title":"Faster Training of Mask R-CNN by Focusing on Instance Boundaries","date":"2018-09-19","arxiv_id":"1809.07069","repositories_listed":2,"syntology":null},{"url":"/paper/on-detection-of-faint-edges-in-noisy-images","title":"On Detection of Faint Edges in Noisy Images","date":"2017-06-22","arxiv_id":"1706.07717","repositories_listed":2,"syntology":null},{"url":"/paper/deepcs-trd-a-deep-learning-based-cross","title":"DeepCS-TRD, a Deep Learning-based Cross-Section Tree Ring Detector","date":"2025-09-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-boundary-detection-in-deep-1","title":"Rethinking Boundary Detection in Deep Learning-Based Medical Image Segmentation","date":"2025-05-06","arxiv_id":"2505.04652","repositories_listed":1,"syntology":null},{"url":"/paper/a-doubly-decoupled-network-for-edge-detection","title":"A Doubly Decoupled Network for edge detection","date":"2025-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/star-edge-structure-aware-local-spherical","title":"STAR-Edge: Structure-aware Local Spherical Curve Representation for Thin-walled Edge Extraction from Unstructured Point Clouds","date":"2025-03-02","arxiv_id":"2503.00801","repositories_listed":1,"syntology":null},{"url":"/paper/agricultural-field-boundary-detection-through","title":"Agricultural Field Boundary Detection through Integration of \"Simple Non-Iterative Clustering (SNIC) Super Pixels\" and \"Canny Edge Detection Method\"","date":"2025-02-06","arxiv_id":"2502.04529","repositories_listed":1,"syntology":null},{"url":"/paper/edmb-edge-detector-with-mamba","title":"EDMB: Edge Detector with Mamba","date":"2025-01-08","arxiv_id":"2501.04846","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-detection-framework-adaptation-for","title":"Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-play Neural Network Toolbox Enabling Edge Deployment","date":"2024-12-24","arxiv_id":"2412.18230","repositories_listed":1,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}