{"url":"/dataset/cbsd68","name":"CBSD68","full_name":"Color BSD68","description_markdown":"**Color BSD68** dataset for image denoising benchmarks is part of The Berkeley Segmentation Dataset and Benchmark. It is used for measuring image denoising algorithms performance. It contains 68 images.\r\n\r\nSource: [https://github.com/clausmichele/CBSD68-dataset](https://github.com/clausmichele/CBSD68-dataset)","description_withheld":null,"homepage":"https://github.com/clausmichele/CBSD68-dataset","introduced_date":"2001-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics","first_author":null,"url":"http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=937655"},"license":{"name":"Custom (research-only, non-commercial)","url":"https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Denoising","url":"/task/denoising","datasets_with_task":"/datasets/task/denoising"},{"name":"Color Image Denoising","url":"/task/color-image-denoising","datasets_with_task":"/datasets/task/color-image-denoising"},{"name":"Image Restoration","url":"/task/image-restoration","datasets_with_task":"/datasets/task/image-restoration"},{"name":"Image Denoising","url":"/task/image-denoising","datasets_with_task":"/datasets/task/image-denoising"},{"name":"Image Compressed Sensing","url":"/task/image-compressed-sensing","datasets_with_task":"/datasets/task/image-compressed-sensing"}],"languages":[],"variants":["CBSD68 sigma70","CBSD68 sigma65","CBSD68 sigma60","CBSD68 sigma55","CBSD68 sigma5","CBSD68 sigma45","CBSD68 sigma40","CBSD68 sigma30","CBSD68 sigma20","CBSD68 sigma10","CBSD68 sigma75","CBSD68 sigma50","CBSD68 sigma35","CBSD68 sigma25","CBSD68 sigma15","CBSD68"],"data_loaders":[{"repo":"https://github.com/clausmichele/CBSD68-dataset","url":"https://github.com/clausmichele/CBSD68-dataset","frameworks":[]}],"num_papers_in_archive":142,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma50","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma50","rows":18,"metrics":["PSNR","LPIPS","SSIM"],"first_row_in_archive_order":{"model":"IPT","paper":"/paper/pre-trained-image-processing-transformer","metrics":{"PSNR":"29.39"},"code_links":[{"title":"huawei-noah/Pretrained-IPT","url":"https://github.com/huawei-noah/Pretrained-IPT"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/IPT"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/IPT"},{"title":"2023-MindSpore-1/ms-code-214","url":"https://github.com/2023-MindSpore-1/ms-code-214/tree/main/IPT"},{"title":"dongyan007/Pretrained-IPT-main-master","url":"https://github.com/dongyan007/Pretrained-IPT-main-master"},{"title":"yangyucheng000/IPT-3","url":"https://github.com/yangyucheng000/IPT-3"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma15","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma15","rows":10,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"AKDT","paper":"/paper/akdt-adaptive-kernel-dilation-transformer-for","metrics":{"PSNR":"34.64"},"code_links":[{"title":"albrateanu/AKDT","url":"https://github.com/albrateanu/AKDT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma25","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma25","rows":9,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"AKDT","paper":"/paper/akdt-adaptive-kernel-dilation-transformer-for","metrics":{"PSNR":"31.94"},"code_links":[{"title":"albrateanu/AKDT","url":"https://github.com/albrateanu/AKDT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma35","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma35","rows":6,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"ADL","paper":"/paper/adversarial-distortion-learning-for-medical","metrics":{"PSNR":"30.24"},"code_links":[{"title":"mogvision/adl","url":"https://github.com/mogvision/adl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma75","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma75","rows":4,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"HyperRes","paper":"/paper/one-size-fits-all-hypernetwork-for-tunable","metrics":{"PSNR":"26.46","SSIM":"0.73"},"code_links":[{"title":"ifryed/HyperRes","url":"https://github.com/ifryed/HyperRes"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma5","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma5","rows":3,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"CBUIFD75","paper":"/paper/blind-universal-bayesian-image-denoising-with","metrics":{"PSNR":"40.05"},"code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma10","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma10","rows":2,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"CBUIFD75","paper":"/paper/blind-universal-bayesian-image-denoising-with","metrics":{"PSNR":"35.98"},"code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma45","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma45","rows":2,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"HyperRes","paper":"/paper/one-size-fits-all-hypernetwork-for-tunable","metrics":{"PSNR":"28.64","SSIM":"0.81"},"code_links":[{"title":"ifryed/HyperRes","url":"https://github.com/ifryed/HyperRes"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma55","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma55","rows":2,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"HyperRes","paper":"/paper/one-size-fits-all-hypernetwork-for-tunable","metrics":{"PSNR":"27.78","SSIM":"0.78"},"code_links":[{"title":"ifryed/HyperRes","url":"https://github.com/ifryed/HyperRes"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma65","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma65","rows":2,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"HyperRes","paper":"/paper/one-size-fits-all-hypernetwork-for-tunable","metrics":{"PSNR":"27.06","SSIM":"0.76"},"code_links":[{"title":"ifryed/HyperRes","url":"https://github.com/ifryed/HyperRes"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma20","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma20","rows":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"CBUIFD75","paper":"/paper/blind-universal-bayesian-image-denoising-with","metrics":{"PSNR":"32.02"},"code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma30","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma30","rows":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"CBUIFD75","paper":"/paper/blind-universal-bayesian-image-denoising-with","metrics":{"PSNR":"29.71"},"code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma40","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma40","rows":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"CBUIFD75","paper":"/paper/blind-universal-bayesian-image-denoising-with","metrics":{"PSNR":"28.01"},"code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma60","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma60","rows":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"CBUIFD75","paper":"/paper/blind-universal-bayesian-image-denoising-with","metrics":{"PSNR":"25.34"},"code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma70","task":"Color Image Denoising","dataset_variant":"CBSD68 sigma70","rows":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"CBUIFD75","paper":"/paper/blind-universal-bayesian-image-denoising-with","metrics":{"PSNR":"24.18"},"code_links":[{"title":"majedelhelou/BUIFD","url":"https://github.com/majedelhelou/BUIFD"},{"title":"IVRL/BUIFD","url":"https://github.com/IVRL/BUIFD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/akdt-adaptive-kernel-dilation-transformer-for","title":"AKDT: Adaptive Kernel Dilation Transformer for Effective Image Denoising","date":"2025-02-26","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/instruct-ipt-all-in-one-image-processing-1","title":"Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation","date":"2024-06-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/residual-conditioned-optimal-transport","title":"Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration","date":"2024-05-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":11,"samples_unverified":1,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stimulating-the-diffusion-model-for-image","title":"Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling","date":"2023-07-08","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/kbnet-kernel-basis-network-for-image","title":"KBNet: Kernel Basis Network for Image Restoration","date":"2023-03-06","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/one-size-fits-all-hypernetwork-for-tunable","title":"Hypernetwork-Based Adaptive Image Restoration","date":"2022-06-13","rows_on_this_dataset":8,"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/adversarial-distortion-learning-for-medical","title":"Adversarial Distortion Learning for Medical Image Denoising","date":"2022-04-29","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/patch-craft-video-denoising-by-deep-modeling","title":"Patch Craft: Video Denoising by Deep Modeling and Patch Matching","date":"2021-03-25","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":4,"samples_unverified":4,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pre-trained-image-processing-transformer","title":"Pre-Trained Image Processing Transformer","date":"2020-12-01","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/rethinking-the-csc-model-for-natural-images","title":"Rethinking the CSC Model for Natural Images","date":"2019-09-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/blind-universal-bayesian-image-denoising-with","title":"Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning","date":"2019-07-05","rows_on_this_dataset":15,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/videnn-deep-blind-video-denoising","title":"ViDeNN: Deep Blind Video Denoising","date":"2019-04-24","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/modulating-image-restoration-with-continual","title":"Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers","date":"2019-04-17","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/real-image-denoising-with-feature-attention","title":"Real Image Denoising with Feature Attention","date":"2019-04-16","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/residual-dense-network-for-image-super","title":"Residual Dense Network for Image Super-Resolution","date":"2018-02-24","rows_on_this_dataset":1,"code_links":16,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":7,"samples_unverified":17,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/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","rows_on_this_dataset":5,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/memnet-a-persistent-memory-network-for-image","title":"MemNet: A Persistent Memory Network for Image Restoration","date":"2017-08-07","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/learning-deep-cnn-denoiser-prior-for-image","title":"Learning Deep CNN Denoiser Prior for Image Restoration","date":"2017-04-11","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/beyond-deep-residual-learning-for-image","title":"Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification","date":"2016-11-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/beyond-a-gaussian-denoiser-residual-learning","title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","date":"2016-08-13","rows_on_this_dataset":1,"code_links":22,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":8,"samples_harvested":70,"samples_ran":31,"samples_unverified":39,"pointer_only_for_licence":21,"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."}