{"url":"/sota/image-enhancement-on-mit-adobe-5k","task":{"name":"Image Enhancement","url":"/task/image-enhancement","note":null},"dataset":{"name":"MIT-Adobe 5k","url":"/dataset/mit-adobe-fivek"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Image Enhancement** is basically improving the interpretability or perception of information in images for human viewers and providing ‘better’ input for other automated image processing techniques. The principal objective of Image Enhancement is to modify attributes of an image to make it more suitable for a given task and a specific observer.\r\n\r\n\r\n<span class=\"description-source\">Source: [A Comprehensive Review of Image Enhancement Techniques ](https://arxiv.org/abs/1003.4053)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["PSNR on sRGB","SSIM on sRGB","PSNR on proRGB","SSIM on proRGB"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"PSNR on sRGB":"higher","SSIM on sRGB":"higher","PSNR on proRGB":"higher","SSIM on proRGB":"higher"}},"counts":{"rows":11,"rows_with_code":9,"rows_with_paper_page":11,"rows_dated":11,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Retinexformer","metrics":{"PSNR on proRGB":"25.98","PSNR on sRGB":"24.94","SSIM on proRGB":"0.957","SSIM on sRGB":"0.907"},"uses_additional_data":false,"paper_date":"2023-03-12","paper":"/paper/retinexformer-one-stage-retinex-based","paper_url":"https://arxiv.org/abs/2303.06705v3","paper_title":"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement","code":"https://github.com/cmhungsteve/Awesome-Transformer-Attention","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":8,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"HG-MTFE","metrics":{"PSNR on proRGB":"25.69"},"uses_additional_data":false,"paper_date":"2024-10-08","paper":"/paper/image-enhancement-based-on-histogram-guided","paper_url":"https://ieeexplore.ieee.org/abstract/document/10707348","paper_title":"Image Enhancement Based on Histogram-Guided Multiple Transformation Function Estimation","code":"https://github.com/PJaemin/HG-MTFE","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"PQDynamicISP","metrics":{"PSNR on proRGB":"25.53","SSIM on proRGB":"0.928"},"uses_additional_data":false,"paper_date":"2024-03-15","paper":"/paper/pqdynamicisp-dynamically-controlled-image","paper_url":"https://arxiv.org/abs/2403.10091v1","paper_title":"PQDynamicISP: Dynamically Controlled Image Signal Processor for Any Image Sensors Pursuing Perceptual Quality","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"AdaInt","metrics":{"PSNR on proRGB":"25.49","SSIM on proRGB":"0.926"},"uses_additional_data":false,"paper_date":"2022-04-29","paper":"/paper/adaint-learning-adaptive-intervals-for-3d","paper_url":"https://arxiv.org/abs/2204.13983v1","paper_title":"AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement","code":"https://github.com/imcharlesy/adaint","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"RSFNet-map","metrics":{"PSNR on proRGB":"25.49","SSIM on proRGB":"0.924"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/rsfnet-a-white-box-image-retouching-approach","paper_url":"https://arxiv.org/abs/2303.08682v2","paper_title":"RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters","code":"https://github.com/vicky0522/rsfnet","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":9,"n_samples":12,"n_pointer_only_licence":12}},{"rank_in_archive_order":6,"model":"SepLUT","metrics":{"PSNR on proRGB":"25.47","SSIM on proRGB":"0.921"},"uses_additional_data":false,"paper_date":"2022-07-18","paper":"/paper/seplut-separable-image-adaptive-lookup-tables","paper_url":"https://arxiv.org/abs/2207.08351v1","paper_title":"SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement","code":"https://github.com/ImCharlesY/SepLUT","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"MTFE","metrics":{"PSNR on proRGB":"25.46"},"uses_additional_data":false,"paper_date":"2023-09-01","paper":"/paper/multiple-transformation-function-estimation","paper_url":"https://doi.org/10.1016/j.jvcir.2023.103863","paper_title":"Multiple transformation function estimation for image enhancement","code":"https://github.com/PJaemin/MTFE","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"3D LUT","metrics":{"PSNR on proRGB":"25.21","SSIM on proRGB":"0.922"},"uses_additional_data":false,"paper_date":"2020-09-30","paper":"/paper/learning-image-adaptive-3d-lookup-tables-for","paper_url":"https://arxiv.org/abs/2009.14468v1","paper_title":"Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time","code":"https://github.com/HuiZeng/Image-Adaptive-3DLUT","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"4D LUT","metrics":{"PSNR on proRGB":"24.61","SSIM on proRGB":"0.918"},"uses_additional_data":false,"paper_date":"2022-09-05","paper":"/paper/4d-lut-learnable-context-aware-4d-lookup","paper_url":"https://arxiv.org/abs/2209.01749v1","paper_title":"4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"DIFAR (MSCA, level 1)","metrics":{"PSNR on proRGB":"24.2","SSIM on proRGB":"0.88"},"uses_additional_data":false,"paper_date":"2019-11-29","paper":"/paper/difar-deep-image-formation-and-retouching","paper_url":"https://arxiv.org/abs/1911.13175v4","paper_title":"CURL: Neural Curve Layers for Global Image Enhancement","code":"https://github.com/sjmoran/neural_curve_layers","n_code_links":3,"syntology":null},{"rank_in_archive_order":11,"model":"DeepLPF","metrics":{"PSNR on proRGB":"23.93","SSIM on proRGB":"0.903"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/deeplpf-deep-local-parametric-filters-for","paper_url":"https://arxiv.org/abs/2003.13985v1","paper_title":"DeepLPF: Deep Local Parametric Filters for Image Enhancement","code":"https://github.com/sjmoran/deep_local_parametric_filters","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":6,"n_unverified":19,"n_samples":25,"n_pointer_only_licence":14,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":6,"n_unverified":19,"n_samples":25,"n_pointer_only_licence":14,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}