{"url":"/sota/grayscale-image-denoising-on-bsd68-sigma25","task":{"name":"Grayscale Image Denoising","url":"/task/grayscale-image-denoising","note":null},"dataset":{"name":"BSD68 sigma25","url":"/dataset/bsd"},"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":["PSNR","SSIM"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"PSNR":"higher","SSIM":"higher"}},"counts":{"rows":16,"rows_with_code":14,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"KBNet","metrics":{"PSNR":"29.54"},"uses_additional_data":false,"paper_date":"2023-03-06","paper":"/paper/kbnet-kernel-basis-network-for-image","paper_url":"https://arxiv.org/abs/2303.02881v1","paper_title":"KBNet: Kernel Basis Network for Image Restoration","code":"https://github.com/zhangyi-3/kbnet","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"ADL","metrics":{"PSNR":"29.50"},"uses_additional_data":false,"paper_date":"2022-04-29","paper":"/paper/adversarial-distortion-learning-for-medical","paper_url":"https://arxiv.org/abs/2204.14100v2","paper_title":"Adversarial Distortion Learning for Medical Image Denoising","code":"https://github.com/mogvision/adl","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"NLRN","metrics":{"PSNR":"29.41"},"uses_additional_data":false,"paper_date":"2018-06-07","paper":"/paper/non-local-recurrent-network-for-image","paper_url":"http://arxiv.org/abs/1806.02919v2","paper_title":"Non-Local Recurrent Network for Image Restoration","code":"https://github.com/Ding-Liu/NLRN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"MWCNN","metrics":{"PSNR":"29.41"},"uses_additional_data":false,"paper_date":"2018-05-18","paper":"/paper/multi-level-wavelet-cnn-for-image-restoration","paper_url":"http://arxiv.org/abs/1805.07071v2","paper_title":"Multi-level Wavelet-CNN for Image Restoration","code":"https://github.com/lpj0/MWCNN","n_code_links":5,"syntology":null},{"rank_in_archive_order":5,"model":"GroupCDL","metrics":{"PSNR":"29.38"},"uses_additional_data":false,"paper_date":"2023-06-02","paper":"/paper/fast-and-interpretable-nonlocal-neural","paper_url":"https://arxiv.org/abs/2306.01950v1","paper_title":"Fast and Interpretable Nonlocal Neural Networks for Image Denoising via Group-Sparse Convolutional Dictionary Learning","code":"https://github.com/nikopj/groupcdl-tip","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"GCDN","metrics":{"PSNR":"29.35"},"uses_additional_data":false,"paper_date":"2019-07-19","paper":"/paper/deep-graph-convolutional-image-denoising","paper_url":"https://arxiv.org/abs/1907.08448v1","paper_title":"Deep Graph-Convolutional Image Denoising","code":"https://github.com/diegovalsesia/gcdn","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"RIDNet","metrics":{"PSNR":"29.34"},"uses_additional_data":false,"paper_date":"2019-04-16","paper":"/paper/real-image-denoising-with-feature-attention","paper_url":"https://arxiv.org/abs/1904.07396v2","paper_title":"Real Image Denoising with Feature Attention","code":"https://github.com/saeed-anwar/RIDNet","n_code_links":3,"syntology":null},{"rank_in_archive_order":8,"model":"N3Net","metrics":{"PSNR":"29.3"},"uses_additional_data":false,"paper_date":"2018-10-30","paper":"/paper/neural-nearest-neighbors-networks","paper_url":"http://arxiv.org/abs/1810.12575v1","paper_title":"Neural Nearest Neighbors Networks","code":"https://github.com/visinf/n3net","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"Big-CDLNet","metrics":{"PSNR":"29.26"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/cdlnet-robust-and-interpretable-denoising","paper_url":"https://arxiv.org/abs/2103.04779v1","paper_title":"CDLNet: Robust and Interpretable Denoising Through Deep Convolutional Dictionary Learning","code":"https://github.com/nikopj/cdlnet-ojsp","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"DnCNN","metrics":{"PSNR":"29.23"},"uses_additional_data":false,"paper_date":"2016-08-13","paper":"/paper/beyond-a-gaussian-denoiser-residual-learning","paper_url":"http://arxiv.org/abs/1608.03981v1","paper_title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","code":"https://github.com/cszn/DnCNN","n_code_links":22,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"FFDNet","metrics":{"PSNR":"29.19"},"uses_additional_data":false,"paper_date":"2017-10-11","paper":"/paper/ffdnet-toward-a-fast-and-flexible-solution","paper_url":"http://arxiv.org/abs/1710.04026v2","paper_title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","code":"https://github.com/cszn/FFDNet","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"SwinIA","metrics":{"PSNR":"29.17","SSIM":"0.801"},"uses_additional_data":false,"paper_date":"2023-05-09","paper":"/paper/swinia-self-supervised-blind-spot-image","paper_url":"https://arxiv.org/abs/2305.05651v2","paper_title":"SwinIA: Self-Supervised Blind-Spot Image Denoising without Convolutions","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"Deep CNN Denoiser","metrics":{"PSNR":"29.15"},"uses_additional_data":false,"paper_date":"2017-04-11","paper":"/paper/learning-deep-cnn-denoiser-prior-for-image","paper_url":"http://arxiv.org/abs/1704.03264v1","paper_title":"Learning Deep CNN Denoiser Prior for Image Restoration","code":"https://github.com/cszn/ircnn","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"Index Network","metrics":{"PSNR":"29.06"},"uses_additional_data":false,"paper_date":"2019-08-11","paper":"/paper/index-network","paper_url":"https://arxiv.org/abs/1908.09895v2","paper_title":"Index Network","code":"https://github.com/poppinace/indexnet_matting","n_code_links":6,"syntology":null},{"rank_in_archive_order":15,"model":"TNRD","metrics":{"PSNR":"28.92"},"uses_additional_data":false,"paper_date":"2015-08-12","paper":"/paper/trainable-nonlinear-reaction-diffusion-a","paper_url":"http://arxiv.org/abs/1508.02848v2","paper_title":"Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"BUIFD75 (blind)","metrics":{"PSNR":"28.75"},"uses_additional_data":false,"paper_date":"2019-07-05","paper":"/paper/blind-universal-bayesian-image-denoising-with","paper_url":"https://arxiv.org/abs/1907.03029v2","paper_title":"Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning","code":"https://github.com/majedelhelou/BUIFD","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}}],"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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":5,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":8,"n_unverified":18,"n_samples":26,"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":8,"n_unverified":18,"n_samples":26,"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"}}}