{"url":"/task/denoising","name":"Denoising","slug":"denoising","description_markdown":"**Denoising** is a task in image processing and computer vision that aims to remove or reduce noise from an image. Noise can be introduced into an image due to various reasons, such as camera sensor limitations, lighting conditions, and compression artifacts. The goal of denoising is to recover the original image, which is considered to be noise-free, from a noisy observation.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Beyond a Gaussian Denoiser](https://arxiv.org/pdf/1608.03981v1.pdf) )</span>","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":7282,"papers_with_code":2838,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"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":23,"subtasks":6,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/denoising-on-darmstadt-noise-dataset","slug":"denoising-on-darmstadt-noise-dataset","dataset":"Darmstadt Noise Dataset","dataset_url":"/dataset/darmstadt-noise-dataset","rows_in_archive":10,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"SINDy","paper_title":"Sparse learning of stochastic dynamic equations","paper_url":"/paper/sparse-learning-of-stochastic-dynamic","paper_date":"2017-12-06","arxiv_id":"1712.02432","code_links":[{"title":"dynamicslab/langevin-regression","url":"https://github.com/dynamicslab/langevin-regression"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}}},{"leaderboard":"/sota/denoising-on-aapm","slug":"denoising-on-aapm","dataset":"AAPM","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"EDCNN","paper_title":"EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising","paper_url":"/paper/edcnn-edge-enhancement-based-densely","paper_date":"2020-10-30","arxiv_id":"2011.00139","code_links":[{"title":"workingcoder/EDCNN","url":"https://github.com/workingcoder/EDCNN"},{"title":"2023-MindSpore-1/ms-code-220","url":"https://github.com/2023-MindSpore-1/ms-code-220/tree/main/EDCN"}],"syntology":null}},{"leaderboard":"/sota/denoising-on-cbsd68-sigm75","slug":"denoising-on-cbsd68-sigm75","dataset":"CBSD68 sigm75","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR/SSIM"],"first_row_in_archive_order":{"model":"MeD","paper_title":"Multi-view Self-supervised Disentanglement for General Image Denoising","paper_url":"/paper/multi-view-self-supervised-disentanglement","paper_date":"2023-09-10","arxiv_id":"2309.05049","code_links":[{"title":"chqwer2/multi-view-self-supervised-disentanglement-denoising","url":"https://github.com/chqwer2/multi-view-self-supervised-disentanglement-denoising"}],"syntology":null}},{"leaderboard":"/sota/denoising-on-div2k","slug":"denoising-on-div2k","dataset":"DIV2K","dataset_url":"/dataset/div2k","rows_in_archive":1,"metrics":["Average PSNR (dB)"],"first_row_in_archive_order":{"model":"DRUnet_Poisson_0.01","paper_title":"Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise","paper_url":"/paper/generalized-recorrupted-to-recorrupted-self","paper_date":"2024-12-05","arxiv_id":"2412.04648","code_links":[{"title":"deepinv/deepinv","url":"https://github.com/deepinv/deepinv"},{"title":"bemc22/GeneralizedR2R","url":"https://github.com/bemc22/GeneralizedR2R"}],"syntology":null}},{"leaderboard":"/sota/denoising-on-dnd-1","slug":"denoising-on-dnd-1","dataset":"DND","dataset_url":"/dataset/dnd","rows_in_archive":1,"metrics":["Average PSNR","SSIM (sRGB)"],"first_row_in_archive_order":{"model":"DRANet","paper_title":"Dual Residual Attention Network for Image Denoising","paper_url":"/paper/dual-residual-attention-network-for-image","paper_date":"2023-05-07","arxiv_id":"2305.04269","code_links":[{"title":"WenCongWu/DRANet","url":"https://github.com/WenCongWu/DRANet"}],"syntology":null}},{"leaderboard":"/sota/denoising-on-iris","slug":"denoising-on-iris","dataset":"iris","dataset_url":"/dataset/iris-1","rows_in_archive":1,"metrics":["Average"],"first_row_in_archive_order":{"model":"PCNN+RL+HME","paper_title":"RH-Net: Improving Neural Relation Extraction via Reinforcement Learning and Hierarchical Relational Searching","paper_url":"/paper/improving-reinforcement-learning-for-neural","paper_date":"2020-10-27","arxiv_id":"2010.14255","code_links":[{"title":"wjn1996/PCNN_RL_HME","url":"https://github.com/wjn1996/PCNN_RL_HME"}],"syntology":null}}],"datasets":[{"url":"/dataset/div2k","name":"DIV2K","full_name":"","num_papers_in_archive":654},{"url":"/dataset/sidd","name":"SIDD","full_name":"Smartphone Image Denoising Dataset","num_papers_in_archive":245},{"url":"/dataset/sid","name":"SID","full_name":"See-in-the-Dark","num_papers_in_archive":155},{"url":"/dataset/cbsd68","name":"CBSD68","full_name":"Color BSD68","num_papers_in_archive":142},{"url":"/dataset/birdsong","name":"BirdSong","full_name":"","num_papers_in_archive":35},{"url":"/dataset/polyu-dataset","name":"PolyU","full_name":"","num_papers_in_archive":34},{"url":"/dataset/crvd","name":"CRVD","full_name":"Captured Raw Video Denoising","num_papers_in_archive":26},{"url":"/dataset/dnd","name":"DND","full_name":"Darmstadt Noise Dataset","num_papers_in_archive":25},{"url":"/dataset/iris-1","name":"iris","full_name":"iris","num_papers_in_archive":20},{"url":"/dataset/fmd","name":"FMD","full_name":"Fluorescence Microscopy Denoising","num_papers_in_archive":17},{"url":"/dataset/darmstadt-noise-dataset","name":"Darmstadt Noise Dataset","full_name":"zaid allal","num_papers_in_archive":13},{"url":"/dataset/nind","name":"NIND","full_name":"Natural Image Noise Dataset","num_papers_in_archive":8},{"url":"/dataset/2detect","name":"2DeteCT","full_name":"2DeteCT - A large 2D expandable, trainable, experimental Computed Tomography dataset for machine learning","num_papers_in_archive":5},{"url":"/dataset/raider","name":"Raider","full_name":"Raider","num_papers_in_archive":5},{"url":"/dataset/s2tld","name":"S2TLD","full_name":"SJTU Small Traffic Light Dataset","num_papers_in_archive":4},{"url":"/dataset/commitbart","name":"CommitBART","full_name":"","num_papers_in_archive":3},{"url":"/dataset/tts-portuguese-corpus","name":"TTS-Portuguese Corpus","full_name":"","num_papers_in_archive":2},{"url":"/dataset/electro-magnetic-emanations-interception","name":"Electro-Magnetic Emanations Interception Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/fingerprint-inpainting-and-denoising","name":"Fingerprint inpainting and denoising","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pixelshift200","name":"PixelShift200","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pointcleannet","name":"PointDenoisingBenchmark","full_name":"","num_papers_in_archive":1},{"url":"/dataset/raw-natural-image-noise-dataset","name":"RawNIND","full_name":"Raw Natural Image Noise Dataset","num_papers_in_archive":1},{"url":"/dataset/pinet","name":"PINet","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/3d-mesh-denoising","name":"3D Mesh Denoising"},{"url":"/task/color-image-denoising","name":"Color Image Denoising"},{"url":"/task/grayscale-image-denoising","name":"Grayscale Image Denoising"},{"url":"/task/image-denoising","name":"Image Denoising"},{"url":"/task/salt-and-pepper-noise-removal","name":"Salt-And-Pepper Noise Removal"},{"url":"/task/sar-image-despeckling","name":"Sar Image Despeckling"}],"parent_tasks":[{"url":"/task/3d-architecture","name":"3D Architecture"}],"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":2838,"tagged_in_all":7282,"items":[{"url":"/paper/denoising-diffusion-probabilistic-models","title":"Denoising Diffusion Probabilistic Models","date":"2020-06-19","arxiv_id":"2006.11239","repositories_listed":70,"syntology":{"n":253,"n_ran":178,"n_unverified":75,"n_pointer_only":62}},{"url":"/paper/bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","arxiv_id":"1910.13461","repositories_listed":47,"syntology":{"n":53,"n_ran":22,"n_unverified":31,"n_pointer_only":7}},{"url":"/paper/high-resolution-image-synthesis-with-latent","title":"High-Resolution Image Synthesis with Latent Diffusion Models","date":"2021-12-20","arxiv_id":"2112.10752","repositories_listed":41,"syntology":{"n":28,"n_ran":19,"n_unverified":9,"n_pointer_only":5}},{"url":"/paper/denoising-diffusion-implicit-models-1","title":"Denoising Diffusion Implicit Models","date":"2020-10-06","arxiv_id":"2010.02502","repositories_listed":29,"syntology":{"n":50,"n_ran":28,"n_unverified":22,"n_pointer_only":5}},{"url":"/paper/beyond-a-gaussian-denoiser-residual-learning","title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","date":"2016-08-13","arxiv_id":"1608.03981","repositories_listed":22,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/noise2noise-learning-image-restoration","title":"Noise2Noise: Learning Image Restoration without Clean Data","date":"2018-03-12","arxiv_id":"1803.04189","repositories_listed":21,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/learning-to-see-in-the-dark","title":"Learning to See in the Dark","date":"2018-05-04","arxiv_id":"1805.01934","repositories_listed":19,"syntology":{"n":14,"n_ran":1,"n_unverified":13,"n_pointer_only":2}},{"url":"/paper/improved-denoising-diffusion-probabilistic-1","title":"Improved Denoising Diffusion Probabilistic Models","date":"2021-02-18","arxiv_id":"2102.09672","repositories_listed":18,"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/image-restoration-using-convolutional-auto","title":"Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections","date":"2016-06-29","arxiv_id":"1606.08921","repositories_listed":17,"syntology":null},{"url":"/paper/deep-image-prior","title":"Deep Image Prior","date":"2017-11-29","arxiv_id":"1711.10925","repositories_listed":14,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":6}},{"url":"/paper/simple-baselines-for-image-restoration","title":"Simple Baselines for Image Restoration","date":"2022-04-10","arxiv_id":"2204.04676","repositories_listed":13,"syntology":{"n":30,"n_ran":23,"n_unverified":7,"n_pointer_only":17}},{"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/neighbor2neighbor-self-supervised-denoising","title":"Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images","date":"2021-01-08","arxiv_id":"2101.02824","repositories_listed":12,"syntology":{"n":13,"n_ran":12,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/learning-enriched-features-for-real-image","title":"Learning Enriched Features for Real Image Restoration and Enhancement","date":"2020-03-15","arxiv_id":"2003.06792","repositories_listed":12,"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":3}},{"url":"/paper/pseudo-numerical-methods-for-diffusion-models-1","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","date":"2022-02-20","arxiv_id":"2202.09778","repositories_listed":9,"syntology":{"n":14,"n_ran":10,"n_unverified":4,"n_pointer_only":2}},{"url":"/paper/wavlm-large-scale-self-supervised-pre","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","date":"2021-10-26","arxiv_id":"2110.13900","repositories_listed":9,"syntology":null},{"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/nbnet-noise-basis-learning-for-image","title":"NBNet: Noise Basis Learning for Image Denoising with Subspace Projection","date":"2020-12-30","arxiv_id":"2012.15028","repositories_listed":9,"syntology":null},{"url":"/paper/low-dose-ct-image-denoising-using-a","title":"Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss","date":"2017-08-03","arxiv_id":"1708.00961","repositories_listed":9,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/multi-stage-progressive-image-restoration","title":"Multi-Stage Progressive Image Restoration","date":"2021-02-04","arxiv_id":"2102.02808","repositories_listed":8,"syntology":{"n":26,"n_ran":18,"n_unverified":8,"n_pointer_only":25}},{"url":"/paper/cycleisp-real-image-restoration-via-improved","title":"CycleISP: Real Image Restoration via Improved Data Synthesis","date":"2020-03-17","arxiv_id":"2003.07761","repositories_listed":8,"syntology":null},{"url":"/paper/multilingual-denoising-pre-training-for","title":"Multilingual Denoising Pre-training for Neural Machine Translation","date":"2020-01-22","arxiv_id":"2001.08210","repositories_listed":8,"syntology":null},{"url":"/paper/ffdnet-toward-a-fast-and-flexible-solution","title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","date":"2017-10-11","arxiv_id":"1710.04026","repositories_listed":8,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/assessment-of-data-consistency-through","title":"Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction","date":"2021-11-30","arxiv_id":"2111.15498","repositories_listed":7,"syntology":null},{"url":"/paper/iterative-gaussianization-from-ica-to-random","title":"Iterative Gaussianization: from ICA to Random Rotations","date":"2016-01-31","arxiv_id":"1602.00229","repositories_listed":7,"syntology":{"n":25,"n_ran":0,"n_unverified":25,"n_pointer_only":0}},{"url":"/paper/structured-denoising-diffusion-models-in","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","date":"2021-07-07","arxiv_id":"2107.03006","repositories_listed":6,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/tsdae-using-transformer-based-sequential","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","date":"2021-04-14","arxiv_id":"2104.06979","repositories_listed":6,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/pre-trained-image-processing-transformer","title":"Pre-Trained Image Processing Transformer","date":"2020-12-01","arxiv_id":"2012.00364","repositories_listed":6,"syntology":null},{"url":"/paper/index-network","title":"Index Network","date":"2019-08-11","arxiv_id":"1908.09895","repositories_listed":6,"syntology":null},{"url":"/paper/improving-grammatical-error-correction-via","title":"Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data","date":"2019-03-01","arxiv_id":"1903.00138","repositories_listed":6,"syntology":null}],"syntology_records":21,"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"}}