{"url":"/dataset/real-blur-dataset","name":"Real Blur Dataset","full_name":null,"description_markdown":"The dataset consists of 4,738 pairs of images of 232 different scenes including reference pairs. All images were captured both in the camera raw and JPEG formats, hence generating two datasets: RealBlur-R from the raw images, and RealBlur-J from the JPEG images. Each training set consists of 3,758 image pairs, while each test set consists of 980 image pairs.\r\n\r\nThe deblurring result is first aligned to its ground truth sharp image using a homography estimated by the enhanced correlation coefficients method, and PSNR or SSIM is computed in sRGB color space.","description_withheld":null,"homepage":"http://cg.postech.ac.kr/research/realblur/","introduced_date":"2020-08-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/real-world-blur-dataset-for-learning-and","title":"Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms","first_author":"Jaesung Rim","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Deblurring","url":"/task/deblurring","datasets_with_task":"/datasets/task/deblurring"},{"name":"Image Deblurring","url":"/task/image-deblurring","datasets_with_task":"/datasets/task/image-deblurring"}],"languages":[],"variants":["RealBlur-J","Real Blur Dataset","RealBlur-R","RealBlur-R (trained on GoPro)","RealBlur-J (trained on GoPro)"],"data_loaders":[{"repo":null,"url":"","frameworks":["pytorch"]}],"num_papers_in_archive":100,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/deblurring-on-realblur-r-trained-on-gopro","task":"Deblurring","dataset_variant":"RealBlur-R (trained on GoPro)","rows":19,"metrics":["PSNR (sRGB)","SSIM (sRGB)"],"first_row_in_archive_order":{"model":"AdaRevD","paper":"/paper/adarevd-adaptive-patch-exiting-reversible-1","metrics":{"PSNR (sRGB)":"36.53","SSIM (sRGB)":"0.957"},"code_links":[{"title":"invokerer/deeprft","url":"https://github.com/invokerer/deeprft"},{"title":"INVOKERer/AdaRevD","url":"https://github.com/INVOKERer/AdaRevD"},{"title":"INVOKERer/LoFormer","url":"https://github.com/INVOKERer/LoFormer"},{"title":"deepmed-lab-ecnu/single-image-deblur","url":"https://github.com/deepmed-lab-ecnu/single-image-deblur"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/deblurring-on-realblur-j-1","task":"Deblurring","dataset_variant":"RealBlur-J","rows":17,"metrics":["PSNR (sRGB)","SSIM (sRGB)","Params(M)"],"first_row_in_archive_order":{"model":"AdaRevD","paper":"/paper/adarevd-adaptive-patch-exiting-reversible-1","metrics":{"PSNR (sRGB)":"33.96","SSIM (sRGB)":"0.944"},"code_links":[{"title":"invokerer/deeprft","url":"https://github.com/invokerer/deeprft"},{"title":"INVOKERer/AdaRevD","url":"https://github.com/INVOKERer/AdaRevD"},{"title":"INVOKERer/LoFormer","url":"https://github.com/INVOKERer/LoFormer"},{"title":"deepmed-lab-ecnu/single-image-deblur","url":"https://github.com/deepmed-lab-ecnu/single-image-deblur"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/deblurring-on-realblur-r","task":"Deblurring","dataset_variant":"RealBlur-R","rows":17,"metrics":["PSNR (sRGB)","SSIM (sRGB)","Params"],"first_row_in_archive_order":{"model":"AdaRevD","paper":"/paper/adarevd-adaptive-patch-exiting-reversible-1","metrics":{"PSNR (sRGB)":"41.19","SSIM (sRGB)":"0.979"},"code_links":[{"title":"invokerer/deeprft","url":"https://github.com/invokerer/deeprft"},{"title":"INVOKERer/AdaRevD","url":"https://github.com/INVOKERer/AdaRevD"},{"title":"INVOKERer/LoFormer","url":"https://github.com/INVOKERer/LoFormer"},{"title":"deepmed-lab-ecnu/single-image-deblur","url":"https://github.com/deepmed-lab-ecnu/single-image-deblur"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/deblurring-on-realblur-j-trained-on-gopro","task":"Deblurring","dataset_variant":"RealBlur-J (trained on GoPro)","rows":15,"metrics":["PSNR (sRGB)","SSIM (sRGB)"],"first_row_in_archive_order":{"model":"AdaRevD","paper":"/paper/adarevd-adaptive-patch-exiting-reversible-1","metrics":{"PSNR (sRGB)":"30.12","SSIM (sRGB)":"0.894"},"code_links":[{"title":"invokerer/deeprft","url":"https://github.com/invokerer/deeprft"},{"title":"INVOKERer/AdaRevD","url":"https://github.com/INVOKERer/AdaRevD"},{"title":"INVOKERer/LoFormer","url":"https://github.com/INVOKERer/LoFormer"},{"title":"deepmed-lab-ecnu/single-image-deblur","url":"https://github.com/deepmed-lab-ecnu/single-image-deblur"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-deblurring-on-realblur-j","task":"Image Deblurring","dataset_variant":"RealBlur-J","rows":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"EVSSM","paper":"/paper/efficient-visual-state-space-model-for-image","metrics":{"PSNR":"34.15","SSIM":"0.945"},"code_links":[{"title":"kkkls/evssm","url":"https://github.com/kkkls/evssm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-deblurring-on-realblur-r","task":"Image Deblurring","dataset_variant":"RealBlur-R","rows":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"EVSSM","paper":"/paper/efficient-visual-state-space-model-for-image","metrics":{"PSNR":"41.04","SSIM":"0.977"},"code_links":[{"title":"kkkls/evssm","url":"https://github.com/kkkls/evssm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/loformer-local-frequency-transformer-for","title":"LoFormer: Local Frequency Transformer for Image Deblurring","date":"2024-07-24","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/adarevd-adaptive-patch-exiting-reversible-1","title":"AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring","date":"2024-06-13","rows_on_this_dataset":4,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":50,"samples_ran":36,"samples_unverified":14,"pointer_only_for_licence":50,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-visual-state-space-model-for-image","title":"Efficient Visual State Space Model for Image Deblurring","date":"2024-05-23","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/aggregating-local-and-global-features-via","title":"Learning Enriched Features via Selective State Spaces Model for Efficient Image Deblurring","date":"2024-03-29","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/deblurdinat-a-lightweight-and-effective","title":"DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains","date":"2024-03-19","rows_on_this_dataset":2,"code_links":1,"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":2,"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/id-blau-image-deblurring-by-implicit","title":"ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation","date":"2023-12-18","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/revisiting-image-deblurring-with-an-efficient","title":"Revisiting Image Deblurring with an Efficient ConvNet","date":"2023-02-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-non-uniform-kernel-estimation","title":"Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring","date":"2023-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficient-frequency-domain-based-transformers","title":"Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring","date":"2022-11-22","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stripformer-strip-transformer-for-fast-image","title":"Stripformer: Strip Transformer for Fast Image Deblurring","date":"2022-04-10","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mssnet-multi-scale-stage-network-for-single","title":"MSSNet: Multi-Scale-Stage Network for Single Image Deblurring","date":"2022-02-19","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/maxim-multi-axis-mlp-for-image-processing","title":"MAXIM: Multi-Axis MLP for Image Processing","date":"2022-01-09","rows_on_this_dataset":5,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":46,"samples_ran":27,"samples_unverified":19,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-residual-fourier-transformation-for","title":"Intriguing Findings of Frequency Selection for Image Deblurring","date":"2021-11-23","rows_on_this_dataset":4,"code_links":5,"syntology":null},{"paper":"/paper/restormer-efficient-transformer-for-high","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","date":"2021-11-18","rows_on_this_dataset":2,"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":1,"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":2,"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":4,"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/banet-blur-aware-attention-networks-for","title":"BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring","date":"2021-01-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/deblurgan-v2-deblurring-orders-of-magnitude","title":"DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better","date":"2019-08-10","rows_on_this_dataset":4,"code_links":6,"syntology":null},{"paper":"/paper/deep-stacked-hierarchical-multi-patch-network","title":"Deep Stacked Hierarchical Multi-patch Network for Image Deblurring","date":"2019-04-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dynamic-scene-deblurring-using-spatially","title":"Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks","date":"2018-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scale-recurrent-network-for-deep-image","title":"Scale-recurrent Network for Deep Image Deblurring","date":"2018-02-06","rows_on_this_dataset":4,"code_links":4,"syntology":null},{"paper":"/paper/deblurgan-blind-motion-deblurring-using","title":"DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks","date":"2017-11-19","rows_on_this_dataset":2,"code_links":13,"syntology":null},{"paper":"/paper/deep-multi-scale-convolutional-neural-network","title":"Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring","date":"2016-12-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/blind-image-deblurring-using-dark-channel","title":"Blind Image Deblurring Using Dark Channel Prior","date":"2016-06-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/deblurring-low-light-images-with-light","title":"Deblurring Low-light Images with Light Streaks","date":"2014-06-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/unnatural-l0-sparse-representation-for","title":"Unnatural L0 Sparse Representation for Natural Image Deblurring","date":"2013-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":12,"samples_harvested":177,"samples_ran":111,"samples_unverified":66,"pointer_only_for_licence":110,"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."}