{"url":"/task/blind-all-in-one-image-restoration","name":"Blind All-in-One Image Restoration","slug":"blind-all-in-one-image-restoration","description_markdown":"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.","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":"derived"},"counts":{"papers_tagged":12,"papers_with_code":10,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/blind-all-in-one-image-restoration-on-3","slug":"blind-all-in-one-image-restoration-on-3","dataset":"3-Degradations","dataset_url":null,"rows_in_archive":9,"metrics":["Average PSNR","SSIM"],"first_row_in_archive_order":{"model":"ABAIR","paper_title":"Adaptive Blind All-in-One Image Restoration","paper_url":"/paper/adaptive-blind-all-in-one-image-restoration","paper_date":"2024-11-27","arxiv_id":"2411.18412","code_links":[{"title":"davidserra9/abair","url":"https://github.com/davidserra9/abair"}],"syntology":null}},{"leaderboard":"/sota/blind-all-in-one-image-restoration-on-5","slug":"blind-all-in-one-image-restoration-on-5","dataset":"5-Degradations","dataset_url":null,"rows_in_archive":9,"metrics":["Average PSNR","SSIM","LPIPS"],"first_row_in_archive_order":{"model":"ABAIR","paper_title":"Adaptive Blind All-in-One Image Restoration","paper_url":"/paper/adaptive-blind-all-in-one-image-restoration","paper_date":"2024-11-27","arxiv_id":"2411.18412","code_links":[{"title":"davidserra9/abair","url":"https://github.com/davidserra9/abair"}],"syntology":null}}],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/unified-image-restoration","name":"Unified Image Restoration"}],"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":10,"of":10,"tagged_in_all":12,"items":[{"url":"/paper/degradation-aware-residual-conditioned","title":"Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration","date":"2024-11-03","arxiv_id":"2411.01656","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/adaptive-blind-all-in-one-image-restoration","title":"Adaptive Blind All-in-One Image Restoration","date":"2024-11-27","arxiv_id":"2411.18412","repositories_listed":1,"syntology":null},{"url":"/paper/restore-anything-with-masks-leveraging-mask","title":"Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration","date":"2024-09-28","arxiv_id":"2409.19403","repositories_listed":1,"syntology":null},{"url":"/paper/hair-hypernetworks-based-all-in-one-image","title":"HAIR: Hypernetworks-based All-in-One Image Restoration","date":"2024-08-15","arxiv_id":"2408.08091","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_unverified":5,"n_pointer_only":18}},{"url":"/paper/any-image-restoration-with-efficient","title":"Restore Anything Model via Efficient Degradation Adaptation","date":"2024-07-18","arxiv_id":"2407.13372","repositories_listed":1,"syntology":null},{"url":"/paper/adair-adaptive-all-in-one-image-restoration","title":"AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation","date":"2024-03-21","arxiv_id":"2403.14614","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/unified-width-adaptive-dynamic-network-for","title":"Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration","date":"2024-01-24","arxiv_id":"2401.13221","repositories_listed":1,"syntology":null},{"url":"/paper/promptir-prompting-for-all-in-one-blind-image","title":"PromptIR: Prompting for All-in-One Blind Image Restoration","date":"2023-06-22","arxiv_id":"2306.13090","repositories_listed":1,"syntology":null},{"url":"/paper/ingredient-oriented-multi-degradation","title":"Ingredient-Oriented Multi-Degradation Learning for Image Restoration","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/all-in-one-image-restoration-for-unknown","title":"All-in-One Image Restoration for Unknown Corruption","date":"2022-01-01","arxiv_id":null,"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"}}