{"url":"/dataset/mef","name":"MEF","full_name":"Multi-exposure image fusion","description_markdown":"Multi-exposure image fusion (MEF) is considered\r\nan effective quality enhancement technique widely adopted in\r\nconsumer electronics, but little work has been dedicated to the\r\nperceptual quality assessment of multi-exposure fused images.\r\nIn this paper, we first build an MEF database and carry\r\nout a subjective user study to evaluate the quality of images\r\ngenerated by different MEF algorithms. There are several useful\r\nfindings. First, considerable agreement has been observed among\r\nhuman subjects on the quality of MEF images. Second, no single\r\nstate-of-the-art MEF algorithm produces the best quality for\r\nall test images. Third, the existing objective quality models for\r\ngeneral image fusion are very limited in predicting perceived\r\nquality of MEF images. Motivated by the lack of appropriate\r\nobjective models, we propose a novel objective image quality\r\nassessment (IQA) algorithm for MEF images based on the\r\nprinciple of the structural similarity approach and a novel\r\nmeasure of patch structural consistency. Our experimental results\r\non the subjective database show that the proposed model well\r\ncorrelates with subjective judgments and significantly outperforms the existing IQA models for general image fusion. Finally,\r\nwe demonstrate the potential application of the proposed model\r\nby automatically tuning the parameters of MEF algorithms","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Low-Light Image Enhancement","url":"/task/low-light-image-enhancement","datasets_with_task":"/datasets/task/low-light-image-enhancement"}],"languages":[],"variants":["MEF"],"data_loaders":[{"repo":"https://github.com/maybeyouorme/MEF_Data","url":"https://github.com/maybeyouorme/MEF_Data","frameworks":[]}],"num_papers_in_archive":9,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/low-light-image-enhancement-on-mef","task":"Low-Light Image Enhancement","dataset_variant":"MEF","rows":7,"metrics":["NIQE","BRISQUE","User Study Score"],"first_row_in_archive_order":{"model":"CIDNet","paper":"/paper/you-only-need-one-color-space-an-efficient","metrics":{"BRISQUE":"13.77","NIQE":"3.11"},"code_links":[{"title":"fediory/hvi-cidnet","url":"https://github.com/fediory/hvi-cidnet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/bayesian-enhancement-models-for-one-to-many","title":"Bayesian Enhancement Models for One-to-Many Mapping in Image Enhancement","date":"2024-10-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/you-only-need-one-color-space-an-efficient","title":"You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement","date":"2024-02-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":1,"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/learning-a-simple-low-light-image-enhancer","title":"Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances","date":"2023-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-low-light-image-enhancement-via","title":"Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior","date":"2021-12-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/zero-reference-deep-curve-estimation-for-low","title":"Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement","date":"2020-01-19","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":1,"samples_unverified":15,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/enlightengan-deep-light-enhancement-without","title":"EnlightenGAN: Deep Light Enhancement without Paired Supervision","date":"2019-06-17","rows_on_this_dataset":1,"code_links":8,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":26,"samples_ran":3,"samples_unverified":23,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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."}