{"url":"/dataset/mit-adobe-fivek","name":"MIT-Adobe FiveK","full_name":null,"description_markdown":"The **MIT-Adobe FiveK** dataset consists of 5,000 photographs taken with SLR cameras by a set of different photographers. They are all in RAW format; that is, all the information recorded by the camera sensor is preserved. We made sure that these photographs cover a broad range of scenes, subjects, and lighting conditions. We then hired five photography students in an art school to adjust the tone of the photos. Each of them retouched all the 5,000 photos using a software dedicated to photo adjustment (Adobe Lightroom) on which they were extensively trained. We asked the retouchers to achieve visually pleasing renditions, akin to a postcard. The retouchers were compensated for their work.\r\n\r\nThis dataset was collected for our project on learning photographic adjustments. When using images from this dataset, please cite this dataset using the following BibTeX:\r\n\r\n```\r\n@inproceedings{fivek,\r\n\tauthor = \"Vladimir Bychkovsky and Sylvain Paris and Eric Chan and Fr{\\'e}do Durand\",\r\n\ttitle = \"Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs\",\r\n\tbooktitle = \"The Twenty-Fourth IEEE Conference on Computer Vision and Pattern Recognition\",\r\n\tyear = \"2011\"\r\n}\r\n```\r\n\r\nSource: [https://data.csail.mit.edu/graphics/fivek/](https://data.csail.mit.edu/graphics/fivek/)\r\n\r\nImage source: [https://data.csail.mit.edu/graphics/fivek/](https://data.csail.mit.edu/graphics/fivek/)","description_withheld":null,"homepage":"https://data.csail.mit.edu/graphics/fivek/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Custom","url":"https://data.csail.mit.edu/graphics/fivek/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Enhancement","url":"/task/image-enhancement","datasets_with_task":"/datasets/task/image-enhancement"},{"name":"Low-Light Image Enhancement","url":"/task/low-light-image-enhancement","datasets_with_task":"/datasets/task/low-light-image-enhancement"},{"name":"Photo Retouching","url":"/task/photo-retouching","datasets_with_task":"/datasets/task/photo-retouching"}],"languages":[],"variants":["MIT-Adobe 5k","MIT-Adobe FiveK"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/logasja/mit-adobe-fivek","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/yuukicammy/mit-adobe-fivek-dataset","url":"https://github.com/yuukicammy/mit-adobe-fivek-dataset","frameworks":["pytorch"]}],"num_papers_in_archive":28,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-enhancement-on-mit-adobe-5k","task":"Image Enhancement","dataset_variant":"MIT-Adobe 5k","rows":11,"metrics":["PSNR on sRGB","SSIM on sRGB","PSNR on proRGB","SSIM on proRGB"],"first_row_in_archive_order":{"model":"Retinexformer","paper":"/paper/retinexformer-one-stage-retinex-based","metrics":{"PSNR on proRGB":"25.98","PSNR on sRGB":"24.94","SSIM on proRGB":"0.957","SSIM on sRGB":"0.907"},"code_links":[{"title":"cmhungsteve/Awesome-Transformer-Attention","url":"https://github.com/cmhungsteve/Awesome-Transformer-Attention"},{"title":"caiyuanhao1998/retinexformer","url":"https://github.com/caiyuanhao1998/retinexformer"},{"title":"DmitryRyumin/ICCV-2023-Papers","url":"https://github.com/DmitryRyumin/ICCV-2023-Papers"},{"title":"lcybuzz/Low-Level-Vision-Paper-Record","url":"https://github.com/lcybuzz/Low-Level-Vision-Paper-Record"},{"title":"dawnlh/awesome-low-light-image-enhancement","url":"https://github.com/dawnlh/awesome-low-light-image-enhancement"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/photo-retouching-on-mit-adobe-5k","task":"Photo Retouching","dataset_variant":"MIT-Adobe 5k","rows":5,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"MAXIM","paper":"/paper/maxim-multi-axis-mlp-for-image-processing","metrics":{"PSNR":"26.15","SSIM":"0.945"},"code_links":[{"title":"google-research/maxim","url":"https://github.com/google-research/maxim"},{"title":"vztu/maxim-pytorch","url":"https://github.com/vztu/maxim-pytorch"},{"title":"sayakpaul/maxim-tf","url":"https://github.com/sayakpaul/maxim-tf"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-enhancement-on-mit-adobe-fivek","task":"Image Enhancement","dataset_variant":"MIT-Adobe FiveK","rows":1,"metrics":["DeltaE","LPIPS","PSNR","SSIM"],"first_row_in_archive_order":{"model":"TreEnhance","paper":"/paper/treenhance-an-automatic-tree-search-based","metrics":{"DeltaE":"11.25","LPIPS":"0.06","PSNR":"21.24","SSIM":"0.89"},"code_links":[{"title":"ocram17/treenhance","url":"https://github.com/ocram17/treenhance"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/low-light-image-enhancement-on-mit-adobe-1","task":"Low-Light Image Enhancement","dataset_variant":"MIT-Adobe FiveK","rows":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Retinexformer","paper":"/paper/retinexformer-one-stage-retinex-based","metrics":{"PSNR":"24.94","SSIM":"0.907"},"code_links":[{"title":"cmhungsteve/Awesome-Transformer-Attention","url":"https://github.com/cmhungsteve/Awesome-Transformer-Attention"},{"title":"caiyuanhao1998/retinexformer","url":"https://github.com/caiyuanhao1998/retinexformer"},{"title":"DmitryRyumin/ICCV-2023-Papers","url":"https://github.com/DmitryRyumin/ICCV-2023-Papers"},{"title":"lcybuzz/Low-Level-Vision-Paper-Record","url":"https://github.com/lcybuzz/Low-Level-Vision-Paper-Record"},{"title":"dawnlh/awesome-low-light-image-enhancement","url":"https://github.com/dawnlh/awesome-low-light-image-enhancement"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/image-enhancement-based-on-histogram-guided","title":"Image Enhancement Based on Histogram-Guided Multiple Transformation Function Estimation","date":"2024-10-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pqdynamicisp-dynamically-controlled-image","title":"PQDynamicISP: Dynamically Controlled Image Signal Processor for Any Image Sensors Pursuing Perceptual Quality","date":"2024-03-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multiple-transformation-function-estimation","title":"Multiple transformation function estimation for image enhancement","date":"2023-09-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rsfnet-a-white-box-image-retouching-approach","title":"RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters","date":"2023-03-15","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":3,"samples_unverified":9,"pointer_only_for_licence":12,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/retinexformer-one-stage-retinex-based","title":"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement","date":"2023-03-12","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":2,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/4d-lut-learnable-context-aware-4d-lookup","title":"4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement","date":"2022-09-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/seplut-separable-image-adaptive-lookup-tables","title":"SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement","date":"2022-07-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/treenhance-an-automatic-tree-search-based","title":"TreEnhance: A Tree Search Method For Low-Light Image Enhancement","date":"2022-05-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaint-learning-adaptive-intervals-for-3d","title":"AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement","date":"2022-04-29","rows_on_this_dataset":2,"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":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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":1,"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/high-resolution-photorealistic-image","title":"High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network","date":"2021-05-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-image-adaptive-3d-lookup-tables-for","title":"Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time","date":"2020-09-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deeplpf-deep-local-parametric-filters-for","title":"DeepLPF: Deep Local Parametric Filters for Image Enhancement","date":"2020-03-31","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/difar-deep-image-formation-and-retouching","title":"CURL: Neural Curve Layers for Global Image Enhancement","date":"2019-11-29","rows_on_this_dataset":2,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":6,"samples_harvested":76,"samples_ran":36,"samples_unverified":40,"pointer_only_for_licence":14,"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."}