{"url":"/dataset/rsblur","name":"RSBlur","full_name":null,"description_markdown":"The RSBlur dataset provides pairs of real and synthetic blurred images with ground truth sharp images. The dataset enables the evaluation of deblurring methods and blur synthesis methods on real-world blurred images.  Training, validation, and test sets consist of 8,878, 1,120, and 3,360 blurred images, respectively.","description_withheld":null,"homepage":"http://cg.postech.ac.kr/research/rsblur","introduced_date":"2022-02-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/realistic-blur-synthesis-for-learning-image","title":"Realistic Blur Synthesis for Learning Image Deblurring","first_author":"Jaesung Rim","url":null},"license":null,"modalities":[],"tasks":[{"name":"Deblurring","url":"/task/deblurring","datasets_with_task":"/datasets/task/deblurring"}],"languages":[],"variants":["RSBlur","RSBlur (trained on synthetic)"],"data_loaders":[],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/deblurring-on-rsblur","task":"Deblurring","dataset_variant":"RSBlur","rows":12,"metrics":["Average PSNR","SSIM"],"first_row_in_archive_order":{"model":"MLWNet","paper":"/paper/efficient-multi-scale-network-with-learnable","metrics":{"Average PSNR":"34.94","SSIM":"0.880"},"code_links":[{"title":"thqiu0419/mlwnet","url":"https://github.com/thqiu0419/mlwnet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/deblurring-on-rsblur-trained-on-synthetic","task":"Deblurring","dataset_variant":"RSBlur (trained on synthetic)","rows":2,"metrics":["Average PSNR"],"first_row_in_archive_order":{"model":"MIMO-UNet + Realistic blur","paper":"/paper/realistic-blur-synthesis-for-learning-image","metrics":{"Average PSNR":"32.08"},"code_links":[{"title":"rimchang/Rsblur","url":"https://github.com/rimchang/Rsblur"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/revitalizing-convolutional-network-for-image","title":"Revitalizing Convolutional Network for Image Restoration","date":"2024-06-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/real-world-efficient-blind-motion-deblurring","title":"Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization","date":"2024-04-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/efficient-multi-scale-network-with-learnable","title":"Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring","date":"2023-12-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":9,"samples_unverified":3,"pointer_only_for_licence":12,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/image-restoration-via-frequency-selection","title":"Image Restoration via Frequency Selection","date":"2023-11-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/irnext-rethinking-convolutional-network","title":"IRNeXt: Rethinking Convolutional Network Design for Image Restoration","date":"2023-04-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/selective-frequency-network-for-image","title":"Selective Frequency Network for Image Restoration","date":"2023-04-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/realistic-blur-synthesis-for-learning-image","title":"Realistic Blur Synthesis for Learning Image Deblurring","date":"2022-02-17","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/restormer-efficient-transformer-for-high","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","date":"2021-11-18","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-coarse-to-fine-approach-in-single","title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","date":"2021-08-11","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":1,"samples_unverified":8,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/uformer-a-general-u-shaped-transformer-for","title":"Uformer: A General U-Shaped Transformer for Image Restoration","date":"2021-06-06","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-stage-progressive-image-restoration","title":"Multi-Stage Progressive Image Restoration","date":"2021-02-04","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":26,"samples_ran":18,"samples_unverified":8,"pointer_only_for_licence":25,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/scale-recurrent-network-for-deep-image","title":"Scale-recurrent Network for Deep Image Deblurring","date":"2018-02-06","rows_on_this_dataset":1,"code_links":4,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":6,"samples_harvested":58,"samples_ran":38,"samples_unverified":20,"pointer_only_for_licence":50,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}