{"url":"/task/image-enhancement","name":"Image Enhancement","slug":"image-enhancement","description_markdown":"**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>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":983,"papers_with_code":445,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":18,"subtasks":10,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/image-enhancement-on-mit-adobe-5k","slug":"image-enhancement-on-mit-adobe-5k","dataset":"MIT-Adobe 5k","dataset_url":"/dataset/mit-adobe-fivek","rows_in_archive":11,"metrics":["PSNR on sRGB","SSIM on sRGB","PSNR on proRGB","SSIM on proRGB"],"first_row_in_archive_order":{"model":"Retinexformer","paper_title":"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement","paper_url":"/paper/retinexformer-one-stage-retinex-based","paper_date":"2023-03-12","arxiv_id":"2303.06705","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"}],"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/image-enhancement-on-tip-2018","slug":"image-enhancement-on-tip-2018","dataset":"TIP 2018","dataset_url":"/dataset/tip-2018","rows_in_archive":6,"metrics":["PSNR","SSIM","FSIM"],"first_row_in_archive_order":{"model":"ESDNet-L","paper_title":"Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing","paper_url":"/paper/towards-efficient-and-scale-robust-ultra-high","paper_date":"2022-07-20","arxiv_id":"2207.09935","code_links":[{"title":"CVMI-Lab/UHDM","url":"https://github.com/CVMI-Lab/UHDM"}],"syntology":null}},{"leaderboard":"/sota/image-enhancement-on-exposure-errors","slug":"image-enhancement-on-exposure-errors","dataset":"Exposure-Errors","dataset_url":"/dataset/exposure-errors","rows_in_archive":5,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"Exposure-slot","paper_title":"Exposure-slot: Exposure-centric representations learning with Slot-in-Slot Attention for Region-aware Exposure Correction","paper_url":"/paper/exposure-slot-exposure-centric","paper_date":"2025-06-11","arxiv_id":null,"code_links":[{"title":"kdhRick2222/Exposure-slot","url":"https://github.com/kdhRick2222/Exposure-slot"}],"syntology":null}},{"leaderboard":"/sota/image-enhancement-on-mit-adobe-fivek","slug":"image-enhancement-on-mit-adobe-fivek","dataset":"MIT-Adobe FiveK","dataset_url":"/dataset/mit-adobe-fivek","rows_in_archive":1,"metrics":["DeltaE","LPIPS","PSNR","SSIM"],"first_row_in_archive_order":{"model":"TreEnhance","paper_title":"TreEnhance: A Tree Search Method For Low-Light Image Enhancement","paper_url":"/paper/treenhance-an-automatic-tree-search-based","paper_date":"2022-05-25","arxiv_id":"2205.12639","code_links":[{"title":"ocram17/treenhance","url":"https://github.com/ocram17/treenhance"}],"syntology":null}},{"leaderboard":"/sota/image-enhancement-on-psnr","slug":"image-enhancement-on-psnr","dataset":"PSNR","dataset_url":null,"rows_in_archive":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"Analyzing Noise Models and Advanced  Filtering Algorithms for Image Enhancement","paper_title":"Analyzing Noise Models and Advanced Filtering Algorithms for Image Enhancement","paper_url":"/paper/analyzing-noise-models-and-advanced-filtering","paper_date":"2024-10-29","arxiv_id":"2410.21946","code_links":[{"title":"SahilAliAkbar/Image_Noise_Analysis","url":"https://github.com/SahilAliAkbar/Image_Noise_Analysis"}],"syntology":null}},{"leaderboard":"/sota/image-enhancement-on-sice-grad","slug":"image-enhancement-on-sice-grad","dataset":"SICE-Grad","dataset_url":"/dataset/sice-grad","rows_in_archive":1,"metrics":["Average PSNR","LPIPS","SSIM"],"first_row_in_archive_order":{"model":"CIDNet","paper_title":"You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement","paper_url":"/paper/you-only-need-one-color-space-an-efficient","paper_date":"2024-02-08","arxiv_id":"2402.05809","code_links":[{"title":"fediory/hvi-cidnet","url":"https://github.com/fediory/hvi-cidnet"}],"syntology":null}},{"leaderboard":"/sota/image-enhancement-on-sice-mix","slug":"image-enhancement-on-sice-mix","dataset":"SICE-Mix","dataset_url":"/dataset/sice-mix","rows_in_archive":1,"metrics":["Average PSNR","LPIPS","SSIM"],"first_row_in_archive_order":{"model":"CIDNet","paper_title":"You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement","paper_url":"/paper/you-only-need-one-color-space-an-efficient","paper_date":"2024-02-08","arxiv_id":"2402.05809","code_links":[{"title":"fediory/hvi-cidnet","url":"https://github.com/fediory/hvi-cidnet"}],"syntology":null}}],"datasets":[{"url":"/dataset/llvip","name":"LLVIP","full_name":"A Visible-infrared Paired Dataset for Low-light Vision","num_papers_in_archive":116},{"url":"/dataset/uieb","name":"UIEB","full_name":"Underwater Image Enhancement Benchmark Dataset","num_papers_in_archive":87},{"url":"/dataset/exdark","name":"ExDark","full_name":"Exclusively Dark Image Dataset","num_papers_in_archive":58},{"url":"/dataset/polyu-dataset","name":"PolyU","full_name":"","num_papers_in_archive":34},{"url":"/dataset/mit-adobe-fivek","name":"MIT-Adobe FiveK","full_name":"","num_papers_in_archive":28},{"url":"/dataset/squid","name":"SQUID","full_name":"Stereo Quantitative Underwater Image Dataset","num_papers_in_archive":24},{"url":"/dataset/exposure-errors","name":"Exposure-Errors","full_name":"","num_papers_in_archive":15},{"url":"/dataset/tip-2018","name":"TIP 2018","full_name":"","num_papers_in_archive":11},{"url":"/dataset/cuhk-image-cropping","name":"CUHK Image Cropping","full_name":"CUHK Image Cropping","num_papers_in_archive":3},{"url":"/dataset/nilut","name":"NILUT","full_name":"NILUT 3D LUT Dataset and enhanced images from MIT5K","num_papers_in_archive":3},{"url":"/dataset/sice-grad","name":"SICE-Grad","full_name":"","num_papers_in_archive":3},{"url":"/dataset/sice-mix","name":"SICE-Mix","full_name":"","num_papers_in_archive":3},{"url":"/dataset/uhdm","name":"UHDM","full_name":"","num_papers_in_archive":2},{"url":"/dataset/canon-raw-low-light","name":"Canon RAW Low Light","full_name":"Canon Camera Low Light RAW Image Dataset","num_papers_in_archive":1},{"url":"/dataset/iirbfd","name":"IRBFD","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nikon-camera-low-light-raw-image-dataset","name":"Nikon RAW Low Light","full_name":"Nikon Camera Low Light RAW Image Dataset","num_papers_in_archive":1},{"url":"/dataset/polarrr","name":"PolarRR","full_name":"","num_papers_in_archive":1},{"url":"/dataset/loli-street","name":"LoLI-Street","full_name":"Low-Light Images of Streets","num_papers_in_archive":0}],"subtasks":[{"url":"/task/color-manipulation","name":"Color Manipulation"},{"url":"/task/de-aliasing","name":"De-aliasing"},{"url":"/task/document-enhancement","name":"Document Enhancement"},{"url":"/task/film-simulation","name":"Film Simulation"},{"url":"/task/image-relighting","name":"Image Relighting"},{"url":"/task/local-color-enhancement","name":"Local Color Enhancement"},{"url":"/task/low-light-image-enhancement","name":"Low-Light Image Enhancement"},{"url":"/task/uie","name":"UIE"},{"url":"/task/vignetting-removal","name":"Vignetting Removal"},{"url":"/task/wavelet-structure-similarity-loss","name":"wavelet structure similarity loss"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":445,"tagged_in_all":983,"items":[{"url":"/paper/zero-reference-deep-curve-estimation-for-low","title":"Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement","date":"2020-01-19","arxiv_id":"2001.06826","repositories_listed":13,"syntology":{"n":16,"n_ran":9,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/learning-enriched-features-for-real-image","title":"Learning Enriched Features for Real Image Restoration and Enhancement","date":"2020-03-15","arxiv_id":"2003.06792","repositories_listed":12,"syntology":{"n":20,"n_ran":12,"n_unverified":8,"n_pointer_only":3}},{"url":"/paper/enlightengan-deep-light-enhancement-without","title":"EnlightenGAN: Deep Light Enhancement without Paired Supervision","date":"2019-06-17","arxiv_id":"1906.06972","repositories_listed":8,"syntology":null},{"url":"/paper/underwater-image-enhancement-via-medium","title":"Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding","date":"2021-04-27","arxiv_id":"2104.13015","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/llnet-a-deep-autoencoder-approach-to-natural","title":"LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement","date":"2015-11-12","arxiv_id":"1511.03995","repositories_listed":6,"syntology":null},{"url":"/paper/retinexformer-one-stage-retinex-based","title":"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement","date":"2023-03-12","arxiv_id":"2303.06705","repositories_listed":5,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/learning-to-enhance-low-light-image-via-zero","title":"Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation","date":"2021-03-01","arxiv_id":"2103.00860","repositories_listed":5,"syntology":null},{"url":"/paper/luminance-guided-chrominance-image","title":"Luminance-Guided Chrominance Image Enhancement for HEVC Intra Coding","date":"2022-06-11","arxiv_id":"2206.05432","repositories_listed":4,"syntology":null},{"url":"/paper/uformer-a-general-u-shaped-transformer-for","title":"Uformer: A General U-Shaped Transformer for Image Restoration","date":"2021-06-06","arxiv_id":"2106.03106","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/projected-distribution-loss-for-image","title":"Projected Distribution Loss for Image Enhancement","date":"2020-12-16","arxiv_id":"2012.09289","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/super-resolution-for-root-imaging","title":"Super Resolution for Root Imaging","date":"2020-03-30","arxiv_id":"2003.13537","repositories_listed":4,"syntology":null},{"url":"/paper/small-object-detection-in-remote-sensing","title":"Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network","date":"2020-03-20","arxiv_id":"2003.09085","repositories_listed":4,"syntology":null},{"url":"/paper/simultaneous-enhancement-and-super-resolution","title":"Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception","date":"2020-02-04","arxiv_id":"2002.01155","repositories_listed":4,"syntology":null},{"url":"/paper/ntire-2024-challenge-on-low-light-image","title":"NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results","date":"2024-04-22","arxiv_id":"2404.14248","repositories_listed":3,"syntology":null},{"url":"/paper/otre-where-optimal-transport-guided-unpaired","title":"OTRE: Where Optimal Transport Guided Unpaired Image-to-Image Translation Meets Regularization by Enhancing","date":"2023-02-06","arxiv_id":"2302.03003","repositories_listed":3,"syntology":null},{"url":"/paper/structure-consistent-restoration-network-for","title":"Structure-consistent Restoration Network for Cataract Fundus Image Enhancement","date":"2022-06-09","arxiv_id":"2206.04684","repositories_listed":3,"syntology":null},{"url":"/paper/lighting-the-darkness-in-the-deep-learning","title":"Low-Light Image and Video Enhancement Using Deep Learning: A Survey","date":"2021-04-21","arxiv_id":"2104.10729","repositories_listed":3,"syntology":null},{"url":"/paper/difar-deep-image-formation-and-retouching","title":"CURL: Neural Curve Layers for Global Image Enhancement","date":"2019-11-29","arxiv_id":"1911.13175","repositories_listed":3,"syntology":null},{"url":"/paper/ris-gan-explore-residual-and-illumination","title":"RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal","date":"2019-11-20","arxiv_id":"1911.09178","repositories_listed":3,"syntology":null},{"url":"/paper/attention-guided-low-light-image-enhancement","title":"Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset","date":"2019-08-02","arxiv_id":"1908.00682","repositories_listed":3,"syntology":null},{"url":"/paper/fast-underwater-image-enhancement-for","title":"Fast Underwater Image Enhancement for Improved Visual Perception","date":"2019-03-23","arxiv_id":"1903.09766","repositories_listed":3,"syntology":null},{"url":"/paper/deep-retinex-decomposition-for-low-light","title":"Deep Retinex Decomposition for Low-Light Enhancement","date":"2018-08-14","arxiv_id":"1808.04560","repositories_listed":3,"syntology":null},{"url":"/paper/single-image-reflection-separation-with","title":"Single Image Reflection Separation with Perceptual Losses","date":"2018-06-14","arxiv_id":"1806.05376","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/getting-to-know-low-light-images-with-the","title":"Getting to Know Low-light Images with The Exclusively Dark Dataset","date":"2018-05-29","arxiv_id":"1805.11227","repositories_listed":3,"syntology":null},{"url":"/paper/deep-burst-denoising","title":"Deep Burst Denoising","date":"2017-12-15","arxiv_id":"1712.05790","repositories_listed":3,"syntology":null},{"url":"/paper/lyt-net-lightweight-yuv-transformer-based","title":"LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancement","date":"2024-01-26","arxiv_id":"2401.15204","repositories_listed":2,"syntology":null},{"url":"/paper/mixnet-towards-effective-and-efficient-uhd","title":"MixNet: Efficient Global Modeling for Ultra-High-Definition Image Restoration","date":"2024-01-19","arxiv_id":"2401.10666","repositories_listed":2,"syntology":null},{"url":"/paper/structure-focused-neurodegeneration","title":"SNeurodCNN: Structure-focused Neurodegeneration Convolutional Neural Network for Modelling and Classification of Alzheimer's Disease","date":"2024-01-08","arxiv_id":"2401.03922","repositories_listed":2,"syntology":null},{"url":"/paper/low-light-image-enhancement-via-clip-fourier","title":"Low-light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion","date":"2024-01-08","arxiv_id":"2401.03788","repositories_listed":2,"syntology":null},{"url":"/paper/boosting-object-detection-with-zero-shot-day","title":"Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation","date":"2023-12-02","arxiv_id":"2312.01220","repositories_listed":2,"syntology":null}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}