{"url":"/task/grayscale-image-denoising","name":"Grayscale Image Denoising","slug":"grayscale-image-denoising","description_markdown":null,"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":13,"papers_with_code":9,"benchmarks":41,"benchmark_tables_in_archive":41,"benchmark_tables_shown":41,"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":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma15","slug":"grayscale-image-denoising-on-bsd68-sigma15","dataset":"BSD68 sigma15","dataset_url":"/dataset/bsd","rows_in_archive":16,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"ADL","paper_title":"Adversarial Distortion Learning for Medical Image Denoising","paper_url":"/paper/adversarial-distortion-learning-for-medical","paper_date":"2022-04-29","arxiv_id":"2204.14100","code_links":[{"title":"mogvision/adl","url":"https://github.com/mogvision/adl"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma25","slug":"grayscale-image-denoising-on-bsd68-sigma25","dataset":"BSD68 sigma25","dataset_url":"/dataset/bsd","rows_in_archive":16,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"KBNet","paper_title":"KBNet: Kernel Basis Network for Image Restoration","paper_url":"/paper/kbnet-kernel-basis-network-for-image","paper_date":"2023-03-06","arxiv_id":"2303.02881","code_links":[{"title":"zhangyi-3/kbnet","url":"https://github.com/zhangyi-3/kbnet"}],"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma50","slug":"grayscale-image-denoising-on-bsd68-sigma50","dataset":"BSD68 sigma50","dataset_url":"/dataset/bsd","rows_in_archive":15,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"ADL","paper_title":"Adversarial Distortion Learning for Medical Image Denoising","paper_url":"/paper/adversarial-distortion-learning-for-medical","paper_date":"2022-04-29","arxiv_id":"2204.14100","code_links":[{"title":"mogvision/adl","url":"https://github.com/mogvision/adl"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma25","slug":"grayscale-image-denoising-on-urban100-sigma25","dataset":"Urban100 sigma25","dataset_url":"/dataset/urban100","rows_in_archive":10,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Hi-IR","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma50","slug":"grayscale-image-denoising-on-urban100-sigma50","dataset":"Urban100 sigma50","dataset_url":"/dataset/urban100","rows_in_archive":10,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Hi-IR","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma15","slug":"grayscale-image-denoising-on-set12-sigma15","dataset":"Set12 sigma15","dataset_url":"/dataset/set12","rows_in_archive":8,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Hi-IR","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma50","slug":"grayscale-image-denoising-on-set12-sigma50","dataset":"Set12 sigma50","dataset_url":"/dataset/set12","rows_in_archive":8,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Hi-IR","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma15","slug":"grayscale-image-denoising-on-urban100-sigma15","dataset":"Urban100 sigma15","dataset_url":"/dataset/urban100","rows_in_archive":7,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Restormer","paper_title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","paper_url":"/paper/restormer-efficient-transformer-for-high","paper_date":"2021-11-18","arxiv_id":"2111.09881","code_links":[{"title":"swz30/restormer","url":"https://github.com/swz30/restormer"},{"title":"swz30/MPRNet","url":"https://github.com/swz30/MPRNet"},{"title":"swz30/MIRNet","url":"https://github.com/swz30/MIRNet"},{"title":"swz30/CycleISP","url":"https://github.com/swz30/CycleISP"},{"title":"swz30/mirnetv2","url":"https://github.com/swz30/mirnetv2"},{"title":"leftthomas/restormer","url":"https://github.com/leftthomas/restormer"},{"title":"MKFMIKU/VIDM","url":"https://github.com/MKFMIKU/VIDM"},{"title":"stephen0808/dnlut","url":"https://github.com/stephen0808/dnlut"},{"title":"HDCVLab/MC-Blur-Dataset","url":"https://github.com/HDCVLab/MC-Blur-Dataset"},{"title":"GarrickZ2/Image-Denoising","url":"https://github.com/GarrickZ2/Image-Denoising"},{"title":"txyugood/Restormer_Paddle","url":"https://github.com/txyugood/Restormer_Paddle"},{"title":"gymoon10/Instance-Segmentation-with-SpatialEmbedding-CA","url":"https://github.com/gymoon10/Instance-Segmentation-with-SpatialEmbedding-CA"},{"title":"prakashSidd18/blind_augmentation","url":"https://github.com/prakashSidd18/blind_augmentation"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}}},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma25","slug":"grayscale-image-denoising-on-set12-sigma25","dataset":"Set12 sigma25","dataset_url":"/dataset/set12","rows_in_archive":6,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Hi-IR","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd200-sigma30","slug":"grayscale-image-denoising-on-bsd200-sigma30","dataset":"BSD200 sigma30","dataset_url":"/dataset/bsd","rows_in_archive":3,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"RC-Net","paper_title":"Image Restoration Using Deep Regulated Convolutional Networks","paper_url":"/paper/image-restoration-using-deep-regulated","paper_date":"2019-10-19","arxiv_id":"1910.08853","code_links":[{"title":"cswin/RC-Nets","url":"https://github.com/cswin/RC-Nets"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd200-sigma50","slug":"grayscale-image-denoising-on-bsd200-sigma50","dataset":"BSD200 sigma50","dataset_url":"/dataset/bsd","rows_in_archive":3,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"RC-Net","paper_title":"Image Restoration Using Deep Regulated Convolutional Networks","paper_url":"/paper/image-restoration-using-deep-regulated","paper_date":"2019-10-19","arxiv_id":"1910.08853","code_links":[{"title":"cswin/RC-Nets","url":"https://github.com/cswin/RC-Nets"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd200-sigma70","slug":"grayscale-image-denoising-on-bsd200-sigma70","dataset":"BSD200 sigma70","dataset_url":"/dataset/bsd","rows_in_archive":3,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"RC-Net","paper_title":"Image Restoration Using Deep Regulated Convolutional Networks","paper_url":"/paper/image-restoration-using-deep-regulated","paper_date":"2019-10-19","arxiv_id":"1910.08853","code_links":[{"title":"cswin/RC-Nets","url":"https://github.com/cswin/RC-Nets"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma70","slug":"grayscale-image-denoising-on-bsd68-sigma70","dataset":"BSD68 sigma70","dataset_url":"/dataset/bsd","rows_in_archive":3,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"N3Net","paper_title":"Neural Nearest Neighbors Networks","paper_url":"/paper/neural-nearest-neighbors-networks","paper_date":"2018-10-30","arxiv_id":"1810.12575","code_links":[{"title":"visinf/n3net","url":"https://github.com/visinf/n3net"},{"title":"Build-Week-Spotify-Song-Suggester-5/Data-Science","url":"https://github.com/Build-Week-Spotify-Song-Suggester-5/Data-Science"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma15-1","slug":"grayscale-image-denoising-on-urban100-sigma15-1","dataset":"urban100 sigma15","dataset_url":"/dataset/urban100","rows_in_archive":3,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Hi-IR","paper_title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","paper_url":"/paper/hierarchical-information-flow-for-generalized","paper_date":"2024-11-27","arxiv_id":"2411.18588","code_links":[],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd200-sigma10","slug":"grayscale-image-denoising-on-bsd200-sigma10","dataset":"BSD200 sigma10","dataset_url":"/dataset/bsd","rows_in_archive":2,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"RC-Net","paper_title":"Image Restoration Using Deep Regulated Convolutional Networks","paper_url":"/paper/image-restoration-using-deep-regulated","paper_date":"2019-10-19","arxiv_id":"1910.08853","code_links":[{"title":"cswin/RC-Nets","url":"https://github.com/cswin/RC-Nets"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma10","slug":"grayscale-image-denoising-on-bsd68-sigma10","dataset":"BSD68 sigma10","dataset_url":"/dataset/bsd","rows_in_archive":2,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Residual Dense Network +","paper_title":"Residual Dense Network for Image Restoration","paper_url":"/paper/residual-dense-network-for-image-restoration","paper_date":"2018-12-25","arxiv_id":"1812.10477","code_links":[{"title":"yulunzhang/RDN","url":"https://github.com/yulunzhang/RDN"},{"title":"QLinhHub/Image-super-resolution","url":"https://github.com/QLinhHub/Image-super-resolution"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/RDN"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma30","slug":"grayscale-image-denoising-on-bsd68-sigma30","dataset":"BSD68 sigma30","dataset_url":"/dataset/bsd","rows_in_archive":2,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Residual Dense Network +","paper_title":"Residual Dense Network for Image Restoration","paper_url":"/paper/residual-dense-network-for-image-restoration","paper_date":"2018-12-25","arxiv_id":"1812.10477","code_links":[{"title":"yulunzhang/RDN","url":"https://github.com/yulunzhang/RDN"},{"title":"QLinhHub/Image-super-resolution","url":"https://github.com/QLinhHub/Image-super-resolution"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/RDN"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma35","slug":"grayscale-image-denoising-on-bsd68-sigma35","dataset":"BSD68 sigma35","dataset_url":"/dataset/bsd","rows_in_archive":2,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"FFDNet","paper_title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","paper_url":"/paper/ffdnet-toward-a-fast-and-flexible-solution","paper_date":"2017-10-11","arxiv_id":"1710.04026","code_links":[{"title":"cszn/FFDNet","url":"https://github.com/cszn/FFDNet"},{"title":"mq0829/DL-CACTI","url":"https://github.com/mq0829/DL-CACTI"},{"title":"Aoi-hosizora/FFDNet_pytorch","url":"https://github.com/Aoi-hosizora/FFDNet_pytorch"},{"title":"7568/ffdnet-pytorch","url":"https://github.com/7568/ffdnet-pytorch"},{"title":"deshanyang/liver-dir-qa","url":"https://github.com/deshanyang/liver-dir-qa"},{"title":"SamirMitha/Denoising","url":"https://github.com/SamirMitha/Denoising"},{"title":"LucasElbert/FFDNet","url":"https://github.com/LucasElbert/FFDNet"},{"title":"deshanyang/abdominal-dir-qa","url":"https://github.com/deshanyang/abdominal-dir-qa"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma75","slug":"grayscale-image-denoising-on-bsd68-sigma75","dataset":"BSD68 sigma75","dataset_url":"/dataset/bsd","rows_in_archive":2,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"FFDNet","paper_title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","paper_url":"/paper/ffdnet-toward-a-fast-and-flexible-solution","paper_date":"2017-10-11","arxiv_id":"1710.04026","code_links":[{"title":"cszn/FFDNet","url":"https://github.com/cszn/FFDNet"},{"title":"mq0829/DL-CACTI","url":"https://github.com/mq0829/DL-CACTI"},{"title":"Aoi-hosizora/FFDNet_pytorch","url":"https://github.com/Aoi-hosizora/FFDNet_pytorch"},{"title":"7568/ffdnet-pytorch","url":"https://github.com/7568/ffdnet-pytorch"},{"title":"deshanyang/liver-dir-qa","url":"https://github.com/deshanyang/liver-dir-qa"},{"title":"SamirMitha/Denoising","url":"https://github.com/SamirMitha/Denoising"},{"title":"LucasElbert/FFDNet","url":"https://github.com/LucasElbert/FFDNet"},{"title":"deshanyang/abdominal-dir-qa","url":"https://github.com/deshanyang/abdominal-dir-qa"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma30","slug":"grayscale-image-denoising-on-set12-sigma30","dataset":"Set12 sigma30","dataset_url":"/dataset/set12","rows_in_archive":2,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"NLRN","paper_title":"Non-Local Recurrent Network for Image Restoration","paper_url":"/paper/non-local-recurrent-network-for-image","paper_date":"2018-06-07","arxiv_id":"1806.02919","code_links":[{"title":"Ding-Liu/NLRN","url":"https://github.com/Ding-Liu/NLRN"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma70","slug":"grayscale-image-denoising-on-urban100-sigma70","dataset":"Urban100 sigma70","dataset_url":"/dataset/urban100","rows_in_archive":2,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Residual Dense Network +","paper_title":"Residual Dense Network for Image Restoration","paper_url":"/paper/residual-dense-network-for-image-restoration","paper_date":"2018-12-25","arxiv_id":"1812.10477","code_links":[{"title":"yulunzhang/RDN","url":"https://github.com/yulunzhang/RDN"},{"title":"QLinhHub/Image-super-resolution","url":"https://github.com/QLinhHub/Image-super-resolution"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/RDN"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma20","slug":"grayscale-image-denoising-on-bsd68-sigma20","dataset":"BSD68 sigma20","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"BUIFD75 (blind)","paper_title":"Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning","paper_url":"/paper/blind-universal-bayesian-image-denoising-with","paper_date":"2019-07-05","arxiv_id":"1907.03029","code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma40","slug":"grayscale-image-denoising-on-bsd68-sigma40","dataset":"BSD68 sigma40","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"BUIFD75 (blind)","paper_title":"Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning","paper_url":"/paper/blind-universal-bayesian-image-denoising-with","paper_date":"2019-07-05","arxiv_id":"1907.03029","code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma45","slug":"grayscale-image-denoising-on-bsd68-sigma45","dataset":"BSD68 sigma45","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"BUIFD75 (blind)","paper_title":"Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning","paper_url":"/paper/blind-universal-bayesian-image-denoising-with","paper_date":"2019-07-05","arxiv_id":"1907.03029","code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma5","slug":"grayscale-image-denoising-on-bsd68-sigma5","dataset":"BSD68 sigma5","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"BUIFD75 (blind)","paper_title":"Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning","paper_url":"/paper/blind-universal-bayesian-image-denoising-with","paper_date":"2019-07-05","arxiv_id":"1907.03029","code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma55","slug":"grayscale-image-denoising-on-bsd68-sigma55","dataset":"BSD68 sigma55","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"BUIFD75 (blind)","paper_title":"Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning","paper_url":"/paper/blind-universal-bayesian-image-denoising-with","paper_date":"2019-07-05","arxiv_id":"1907.03029","code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma60","slug":"grayscale-image-denoising-on-bsd68-sigma60","dataset":"BSD68 sigma60","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"BUIFD75 (blind)","paper_title":"Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning","paper_url":"/paper/blind-universal-bayesian-image-denoising-with","paper_date":"2019-07-05","arxiv_id":"1907.03029","code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma65","slug":"grayscale-image-denoising-on-bsd68-sigma65","dataset":"BSD68 sigma65","dataset_url":"/dataset/bsd","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"BUIFD75 (blind)","paper_title":"Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning","paper_url":"/paper/blind-universal-bayesian-image-denoising-with","paper_date":"2019-07-05","arxiv_id":"1907.03029","code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-clip300-sigma15","slug":"grayscale-image-denoising-on-clip300-sigma15","dataset":"Clip300 sigma15","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"FFDNet-Clip","paper_title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","paper_url":"/paper/ffdnet-toward-a-fast-and-flexible-solution","paper_date":"2017-10-11","arxiv_id":"1710.04026","code_links":[{"title":"cszn/FFDNet","url":"https://github.com/cszn/FFDNet"},{"title":"mq0829/DL-CACTI","url":"https://github.com/mq0829/DL-CACTI"},{"title":"Aoi-hosizora/FFDNet_pytorch","url":"https://github.com/Aoi-hosizora/FFDNet_pytorch"},{"title":"7568/ffdnet-pytorch","url":"https://github.com/7568/ffdnet-pytorch"},{"title":"deshanyang/liver-dir-qa","url":"https://github.com/deshanyang/liver-dir-qa"},{"title":"SamirMitha/Denoising","url":"https://github.com/SamirMitha/Denoising"},{"title":"LucasElbert/FFDNet","url":"https://github.com/LucasElbert/FFDNet"},{"title":"deshanyang/abdominal-dir-qa","url":"https://github.com/deshanyang/abdominal-dir-qa"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-clip300-sigma25","slug":"grayscale-image-denoising-on-clip300-sigma25","dataset":"Clip300 sigma25","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"FFDNet-Clip","paper_title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","paper_url":"/paper/ffdnet-toward-a-fast-and-flexible-solution","paper_date":"2017-10-11","arxiv_id":"1710.04026","code_links":[{"title":"cszn/FFDNet","url":"https://github.com/cszn/FFDNet"},{"title":"mq0829/DL-CACTI","url":"https://github.com/mq0829/DL-CACTI"},{"title":"Aoi-hosizora/FFDNet_pytorch","url":"https://github.com/Aoi-hosizora/FFDNet_pytorch"},{"title":"7568/ffdnet-pytorch","url":"https://github.com/7568/ffdnet-pytorch"},{"title":"deshanyang/liver-dir-qa","url":"https://github.com/deshanyang/liver-dir-qa"},{"title":"SamirMitha/Denoising","url":"https://github.com/SamirMitha/Denoising"},{"title":"LucasElbert/FFDNet","url":"https://github.com/LucasElbert/FFDNet"},{"title":"deshanyang/abdominal-dir-qa","url":"https://github.com/deshanyang/abdominal-dir-qa"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-clip300-sigma35","slug":"grayscale-image-denoising-on-clip300-sigma35","dataset":"Clip300 sigma35","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"FFDNet-Clip","paper_title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","paper_url":"/paper/ffdnet-toward-a-fast-and-flexible-solution","paper_date":"2017-10-11","arxiv_id":"1710.04026","code_links":[{"title":"cszn/FFDNet","url":"https://github.com/cszn/FFDNet"},{"title":"mq0829/DL-CACTI","url":"https://github.com/mq0829/DL-CACTI"},{"title":"Aoi-hosizora/FFDNet_pytorch","url":"https://github.com/Aoi-hosizora/FFDNet_pytorch"},{"title":"7568/ffdnet-pytorch","url":"https://github.com/7568/ffdnet-pytorch"},{"title":"deshanyang/liver-dir-qa","url":"https://github.com/deshanyang/liver-dir-qa"},{"title":"SamirMitha/Denoising","url":"https://github.com/SamirMitha/Denoising"},{"title":"LucasElbert/FFDNet","url":"https://github.com/LucasElbert/FFDNet"},{"title":"deshanyang/abdominal-dir-qa","url":"https://github.com/deshanyang/abdominal-dir-qa"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-clip300-sigma50","slug":"grayscale-image-denoising-on-clip300-sigma50","dataset":"Clip300 sigma50","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"FFDNet-Clip","paper_title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","paper_url":"/paper/ffdnet-toward-a-fast-and-flexible-solution","paper_date":"2017-10-11","arxiv_id":"1710.04026","code_links":[{"title":"cszn/FFDNet","url":"https://github.com/cszn/FFDNet"},{"title":"mq0829/DL-CACTI","url":"https://github.com/mq0829/DL-CACTI"},{"title":"Aoi-hosizora/FFDNet_pytorch","url":"https://github.com/Aoi-hosizora/FFDNet_pytorch"},{"title":"7568/ffdnet-pytorch","url":"https://github.com/7568/ffdnet-pytorch"},{"title":"deshanyang/liver-dir-qa","url":"https://github.com/deshanyang/liver-dir-qa"},{"title":"SamirMitha/Denoising","url":"https://github.com/SamirMitha/Denoising"},{"title":"LucasElbert/FFDNet","url":"https://github.com/LucasElbert/FFDNet"},{"title":"deshanyang/abdominal-dir-qa","url":"https://github.com/deshanyang/abdominal-dir-qa"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-clip300-sigma60","slug":"grayscale-image-denoising-on-clip300-sigma60","dataset":"Clip300 sigma60","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"FFDNet-Clip","paper_title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","paper_url":"/paper/ffdnet-toward-a-fast-and-flexible-solution","paper_date":"2017-10-11","arxiv_id":"1710.04026","code_links":[{"title":"cszn/FFDNet","url":"https://github.com/cszn/FFDNet"},{"title":"mq0829/DL-CACTI","url":"https://github.com/mq0829/DL-CACTI"},{"title":"Aoi-hosizora/FFDNet_pytorch","url":"https://github.com/Aoi-hosizora/FFDNet_pytorch"},{"title":"7568/ffdnet-pytorch","url":"https://github.com/7568/ffdnet-pytorch"},{"title":"deshanyang/liver-dir-qa","url":"https://github.com/deshanyang/liver-dir-qa"},{"title":"SamirMitha/Denoising","url":"https://github.com/SamirMitha/Denoising"},{"title":"LucasElbert/FFDNet","url":"https://github.com/LucasElbert/FFDNet"},{"title":"deshanyang/abdominal-dir-qa","url":"https://github.com/deshanyang/abdominal-dir-qa"}],"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/grayscale-image-denoising-on-hanzi","slug":"grayscale-image-denoising-on-hanzi","dataset":"Hanzi","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"SwinIA","paper_title":"SwinIA: Self-Supervised Blind-Spot Image Denoising without Convolutions","paper_url":"/paper/swinia-self-supervised-blind-spot-image","paper_date":"2023-05-09","arxiv_id":"2305.05651","code_links":[],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-kodak24-sigma10","slug":"grayscale-image-denoising-on-kodak24-sigma10","dataset":"Kodak24 sigma10","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Residual Dense Network +","paper_title":"Residual Dense Network for Image Restoration","paper_url":"/paper/residual-dense-network-for-image-restoration","paper_date":"2018-12-25","arxiv_id":"1812.10477","code_links":[{"title":"yulunzhang/RDN","url":"https://github.com/yulunzhang/RDN"},{"title":"QLinhHub/Image-super-resolution","url":"https://github.com/QLinhHub/Image-super-resolution"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/RDN"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-kodak24-sigma30","slug":"grayscale-image-denoising-on-kodak24-sigma30","dataset":"Kodak24 sigma30","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Residual Dense Network +","paper_title":"Residual Dense Network for Image Restoration","paper_url":"/paper/residual-dense-network-for-image-restoration","paper_date":"2018-12-25","arxiv_id":"1812.10477","code_links":[{"title":"yulunzhang/RDN","url":"https://github.com/yulunzhang/RDN"},{"title":"QLinhHub/Image-super-resolution","url":"https://github.com/QLinhHub/Image-super-resolution"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/RDN"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-kodak24-sigma50","slug":"grayscale-image-denoising-on-kodak24-sigma50","dataset":"Kodak24 sigma50","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Residual Dense Network +","paper_title":"Residual Dense Network for Image Restoration","paper_url":"/paper/residual-dense-network-for-image-restoration","paper_date":"2018-12-25","arxiv_id":"1812.10477","code_links":[{"title":"yulunzhang/RDN","url":"https://github.com/yulunzhang/RDN"},{"title":"QLinhHub/Image-super-resolution","url":"https://github.com/QLinhHub/Image-super-resolution"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/RDN"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-kodak24-sigma70","slug":"grayscale-image-denoising-on-kodak24-sigma70","dataset":"Kodak24 sigma70","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Residual Dense Network +","paper_title":"Residual Dense Network for Image Restoration","paper_url":"/paper/residual-dense-network-for-image-restoration","paper_date":"2018-12-25","arxiv_id":"1812.10477","code_links":[{"title":"yulunzhang/RDN","url":"https://github.com/yulunzhang/RDN"},{"title":"QLinhHub/Image-super-resolution","url":"https://github.com/QLinhHub/Image-super-resolution"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/RDN"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma70","slug":"grayscale-image-denoising-on-set12-sigma70","dataset":"Set12 sigma70","dataset_url":"/dataset/set12","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"N3Net","paper_title":"Neural Nearest Neighbors Networks","paper_url":"/paper/neural-nearest-neighbors-networks","paper_date":"2018-10-30","arxiv_id":"1810.12575","code_links":[{"title":"visinf/n3net","url":"https://github.com/visinf/n3net"},{"title":"Build-Week-Spotify-Song-Suggester-5/Data-Science","url":"https://github.com/Build-Week-Spotify-Song-Suggester-5/Data-Science"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma10","slug":"grayscale-image-denoising-on-urban100-sigma10","dataset":"Urban100 sigma10","dataset_url":"/dataset/urban100","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Residual Dense Network +","paper_title":"Residual Dense Network for Image Restoration","paper_url":"/paper/residual-dense-network-for-image-restoration","paper_date":"2018-12-25","arxiv_id":"1812.10477","code_links":[{"title":"yulunzhang/RDN","url":"https://github.com/yulunzhang/RDN"},{"title":"QLinhHub/Image-super-resolution","url":"https://github.com/QLinhHub/Image-super-resolution"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/RDN"}],"syntology":null}},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma30","slug":"grayscale-image-denoising-on-urban100-sigma30","dataset":"Urban100 sigma30","dataset_url":"/dataset/urban100","rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Residual Dense Network +","paper_title":"Residual Dense Network for Image Restoration","paper_url":"/paper/residual-dense-network-for-image-restoration","paper_date":"2018-12-25","arxiv_id":"1812.10477","code_links":[{"title":"yulunzhang/RDN","url":"https://github.com/yulunzhang/RDN"},{"title":"QLinhHub/Image-super-resolution","url":"https://github.com/QLinhHub/Image-super-resolution"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/RDN"}],"syntology":null}}],"datasets":[{"url":"/dataset/bsd","name":"BSD","full_name":"Berkeley Segmentation Dataset","num_papers_in_archive":718},{"url":"/dataset/urban100","name":"Urban100","full_name":"","num_papers_in_archive":591},{"url":"/dataset/set12","name":"Set12","full_name":"","num_papers_in_archive":145}],"subtasks":[],"parent_tasks":[{"url":"/task/denoising","name":"Denoising"}],"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":9,"of":9,"tagged_in_all":13,"items":[{"url":"/paper/restormer-efficient-transformer-for-high","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","date":"2021-11-18","arxiv_id":"2111.09881","repositories_listed":13,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/swinir-image-restoration-using-swin","title":"SwinIR: Image Restoration Using Swin Transformer","date":"2021-08-23","arxiv_id":"2108.10257","repositories_listed":9,"syntology":{"n":45,"n_ran":30,"n_unverified":15,"n_pointer_only":5}},{"url":"/paper/index-network","title":"Index Network","date":"2019-08-11","arxiv_id":"1908.09895","repositories_listed":6,"syntology":null},{"url":"/paper/revisiting-global-statistics-aggregation-for","title":"Improving Image Restoration by Revisiting Global Information Aggregation","date":"2021-12-08","arxiv_id":"2112.04491","repositories_listed":3,"syntology":null},{"url":"/paper/fast-and-interpretable-nonlocal-neural","title":"Fast and Interpretable Nonlocal Neural Networks for Image Denoising via Group-Sparse Convolutional Dictionary Learning","date":"2023-06-02","arxiv_id":"2306.01950","repositories_listed":1,"syntology":null},{"url":"/paper/kbnet-kernel-basis-network-for-image","title":"KBNet: Kernel Basis Network for Image Restoration","date":"2023-03-06","arxiv_id":"2303.02881","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/adversarial-distortion-learning-for-medical","title":"Adversarial Distortion Learning for Medical Image Denoising","date":"2022-04-29","arxiv_id":"2204.14100","repositories_listed":1,"syntology":null},{"url":"/paper/cdlnet-robust-and-interpretable-denoising","title":"CDLNet: Robust and Interpretable Denoising Through Deep Convolutional Dictionary Learning","date":"2021-03-05","arxiv_id":"2103.04779","repositories_listed":1,"syntology":null},{"url":"/paper/low-weight-and-learnable-image-denoising","title":"LIDIA: Lightweight Learned Image Denoising with Instance Adaptation","date":"2019-11-17","arxiv_id":"1911.07167","repositories_listed":1,"syntology":null}],"syntology_records":3,"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"}}