{"url":"/sota/blind-all-in-one-image-restoration-on-3","task":{"name":"Blind All-in-One Image Restoration","url":"/task/blind-all-in-one-image-restoration","note":null},"dataset":{"name":"3-Degradations","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Blind All-in-One Image Restoration aims to remove various degradations from an input image without prior knowledge of the degradation type or severity. This task is evaluated under two setups: three-degradation and five-degradation.\r\n\r\nThree-Degradation Setup:
The objective is to restore images affected by rain, haze, and noise. Training datasets include Rain200L for deraining, RESIDE for dehazing, and WED and BSD400 for denoising with noise levels σ = 15, 25, 50. Evaluation datasets are Rain100L for deraining, SOTS (outdoor) for dehazing, and BSD68 for denoising with σ = 15, 25, 50.\r\n\r\nFive-Degradation Setup:
This setup expands to include five common image restoration tasks: rain, haze, noise, blur, and low-light conditions. Training datasets comprise Rain200L for deraining, RESIDE for dehazing, WED and BSD400 for denoising (σ = 25), GoPro for deblurring, and LoLv1 for low-light enhancement. Evaluation uses Rain100L for deraining, SOTS (outdoor) for dehazing, BSD68 for denoising (σ = 25), GoPro for deblurring, and LoLv1 for low-light enhancement.\r\n\r\nPerformance Metrics:
Model performance is assessed by reporting the average PSNR and SSIM across all evaluation datasets, reflecting the overall capability to handle diverse degradations. This task challenges models to effectively restore images across multiple degradation types without specific knowledge of the degradation, emphasizing versatility and robustness in image restoration techniques.","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":["Average 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":{"Average PSNR":"higher","SSIM":"higher"}},"counts":{"rows":9,"rows_with_code":8,"rows_with_paper_page":9,"rows_dated":9,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ABAIR","metrics":{"Average PSNR":"33.21","SSIM":"0.919"},"uses_additional_data":false,"paper_date":"2024-11-27","paper":"/paper/adaptive-blind-all-in-one-image-restoration","paper_url":"https://arxiv.org/abs/2411.18412v1","paper_title":"Adaptive Blind All-in-One Image Restoration","code":"https://github.com/davidserra9/abair","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"MoCE-IR","metrics":{"Average PSNR":"32.73","SSIM":"0.917"},"uses_additional_data":false,"paper_date":"2024-11-27","paper":"/paper/complexity-experts-are-task-discriminative","paper_url":"https://arxiv.org/abs/2411.18466v1","paper_title":"Complexity Experts are Task-Discriminative Learners for Any Image Restoration","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"HAIR","metrics":{"Average PSNR":"32.70","SSIM":"0.919"},"uses_additional_data":false,"paper_date":"2024-08-15","paper":"/paper/hair-hypernetworks-based-all-in-one-image","paper_url":"https://arxiv.org/abs/2408.08091v4","paper_title":"HAIR: Hypernetworks-based All-in-One Image Restoration","code":"https://github.com/toummHus/HAIR","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":5,"n_samples":18,"n_pointer_only_licence":18}},{"rank_in_archive_order":4,"model":"AdaIR","metrics":{"Average PSNR":"32.69","SSIM":"0.918"},"uses_additional_data":false,"paper_date":"2024-03-21","paper":"/paper/adair-adaptive-all-in-one-image-restoration","paper_url":"https://arxiv.org/abs/2403.14614v1","paper_title":"AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation","code":"https://github.com/c-yn/adair","n_code_links":1,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"DA-RCOT","metrics":{"Average PSNR":"32.60","SSIM":"0.917"},"uses_additional_data":false,"paper_date":"2024-11-03","paper":"/paper/degradation-aware-residual-conditioned","paper_url":"https://arxiv.org/abs/2411.01656v1","paper_title":"Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration","code":"https://github.com/xl-tang3/RCOT","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":6,"model":"RAM","metrics":{"Average PSNR":"32.51","SSIM":"0.916"},"uses_additional_data":false,"paper_date":"2024-07-18","paper":"/paper/any-image-restoration-with-efficient","paper_url":"https://arxiv.org/abs/2407.13372v2","paper_title":"Restore Anything Model via Efficient Degradation Adaptation","code":"https://github.com/Amazingren/AnyIR","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"PromptIR","metrics":{"Average PSNR":"32.06","SSIM":"0.913"},"uses_additional_data":false,"paper_date":"2023-06-22","paper":"/paper/promptir-prompting-for-all-in-one-blind-image","paper_url":"https://arxiv.org/abs/2306.13090v1","paper_title":"PromptIR: Prompting for All-in-One Blind Image Restoration","code":"https://github.com/va1shn9v/promptir","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"U-WADN","metrics":{"Average PSNR":"31.47","SSIM":"0.910"},"uses_additional_data":false,"paper_date":"2024-01-24","paper":"/paper/unified-width-adaptive-dynamic-network-for","paper_url":"https://arxiv.org/abs/2401.13221v1","paper_title":"Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration","code":"https://github.com/xuyimin0926/u-wadn","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"AirNet","metrics":{"Average PSNR":"31.20","SSIM":"0.910"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/all-in-one-image-restoration-for-unknown","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Li_All-in-One_Image_Restoration_for_Unknown_Corruption_CVPR_2022_paper.html","paper_title":"All-in-One Image Restoration for Unknown Corruption","code":"https://github.com/xlearning-scu/2022-cvpr-airnet","n_code_links":1,"syntology":null}],"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":31,"n_unverified":8,"n_samples":39,"n_pointer_only_licence":24,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":31,"n_unverified":8,"n_samples":39,"n_pointer_only_licence":24,"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"}}}