{"url":"/dataset/msu-video-quality-metrics-benchmark","name":"MSU NR VQA Database","full_name":"MSU No-Reference Video Quality Assessment Database","description_markdown":"The dataset was created for video quality assessment problem. It was formed with 36 clips from Vimeo, which were selected from 18,000+ open-source clips with high bitrate (license CCBY or CC0). \r\n\r\nThe clips include videos recorded by both professionals and amateurs. Almost half of the videos contain scene changes and high dynamism. Moreover, the synthetic to natural lightning ratio is approximately 1 to 3.\r\n\r\n* Content type: nature, sport, humans close up, gameplays, music videos, water stream or steam, CGI\r\n* Effects and distortions: shaking, slow-motion, grain/noisy, too dark/bright regions, macro shooting, captions (text), extraneous objects on the camera lens or just close to it\r\n* Resolution: 1920x1080 as the most popular modern video resolution (more in the future)\r\n* Format: yuv420p\r\n* FPS: 24, 25, 30, 39, 50, 60\r\n* Videos duration: mainly 10 seconds\r\n\r\nSuch content diversity helps simulate near-realistic conditions.\r\nThe choice of videos collected for the benchmark dataset employed clustering in terms of space-time complexity to obtain a representative distribution.\r\n\r\nFor compression we used 40 codecs of 10 compression standards (H.264, AV1, H.265, VVC, etc.). Each video was compressed with 3 target bitrates: 1,000 Kbps, 2,000 Kbps, and 4,000 Kbps, and different real-life encoding modes: constant quality (CRF) and variable bitrate (VBR). The choice of bitrate range simplifies the subjective comparison procedure since the video quality is more difficult to distinguish visually at higher bitrates. \r\n\r\nThe subjective assessment involved pairwise comparisons using crowdsourcing service Subjectify.us. To increase the relevance of the results, each pair of videos received at least 10 responses from participants. In total, 766362 valid answers were collected from more than 10800 unique participants.","description_withheld":null,"homepage":"https://videoprocessing.ai/benchmarks/no-reference-video-quality-metrics.html","introduced_date":"2022-11-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/video-compression-dataset-and-benchmark-of","title":"Video compression dataset and benchmark of learning-based video-quality metrics","first_author":"Anastasia Antsiferova","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Image Quality Assessment","url":"/task/image-quality-assessment","datasets_with_task":"/datasets/task/image-quality-assessment"},{"name":"Video Quality Assessment","url":"/task/video-quality-assessment","datasets_with_task":"/datasets/task/video-quality-assessment"},{"name":"No-Reference Image Quality Assessment","url":"/task/no-reference-image-quality-assessment","datasets_with_task":"/datasets/task/no-reference-image-quality-assessment"},{"name":"Blind Image Quality Assessment","url":"/task/blind-image-quality-assessment","datasets_with_task":"/datasets/task/blind-image-quality-assessment"}],"languages":[],"variants":["MSU NR VQA Database"],"data_loaders":[],"num_papers_in_archive":20,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-quality-assessment-on-msu-video-quality","task":"Video Quality Assessment","dataset_variant":"MSU NR VQA Database","rows":21,"metrics":["SRCC","PLCC","KLCC","Type"],"first_row_in_archive_order":{"model":"MDTVSFA","paper":"/paper/unified-quality-assessment-of-in-the-wild","metrics":{"KLCC":"0.7883","PLCC":"0.9431","SRCC":"0.9289","Type":"NR"},"code_links":[{"title":"lidq92/MDTVSFA","url":"https://github.com/lidq92/MDTVSFA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-quality-assessment-on-msu-nr-vqa","task":"Image Quality Assessment","dataset_variant":"MSU NR VQA Database","rows":10,"metrics":["SRCC","PLCC","KLCC"],"first_row_in_archive_order":{"model":"UNIQUE","paper":"/paper/unique-unsupervised-image-quality-estimation","metrics":{"KLCC":"0.7648","PLCC":"0.9238","SRCC":"0.9148"},"code_links":[{"title":"olivesgatech/UNIQUE-Unsupervised-Image-Quality-Estimation","url":"https://github.com/olivesgatech/UNIQUE-Unsupervised-Image-Quality-Estimation"},{"title":"olivesgatech/UNIQUE-Project-Repository","url":"https://github.com/olivesgatech/UNIQUE-Project-Repository"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/disentangling-aesthetic-and-technical-effects","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","date":"2022-11-09","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fast-vqa-efficient-end-to-end-video-quality","title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","date":"2022-07-06","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/blindly-assess-quality-of-in-the-wild-videos","title":"Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception","date":"2021-08-19","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/musiq-multi-scale-image-quality-transformer","title":"MUSIQ: Multi-scale Image Quality Transformer","date":"2021-08-12","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-learning-based-full-reference-and-no","title":"Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos","date":"2021-06-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/unified-quality-assessment-of-in-the-wild","title":"Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training","date":"2020-11-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/norm-in-norm-loss-with-faster-convergence-and","title":"Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessment","date":"2020-08-10","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/perceptual-quality-assessment-of-smartphone","title":"Perceptual Quality Assessment of Smartphone Photography","date":"2020-06-01","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/ugc-vqa-benchmarking-blind-video-quality","title":"UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content","date":"2020-05-29","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/from-patches-to-pictures-paq-2-piq-mapping","title":"From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality","date":"2019-12-20","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/koniq-10k-an-ecologically-valid-database-for","title":"KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment","date":"2019-10-14","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/quality-assessment-of-in-the-wild-videos","title":"Quality Assessment of In-the-Wild Videos","date":"2019-08-01","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/barriers-towards-no-reference-metrics","title":"Barriers towards no-reference metrics application to compressed video quality analysis: on the example of no-reference metric NIQE","date":"2019-07-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/blind-image-quality-assessment-using-a-deep","title":"Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network","date":"2019-07-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":10,"samples_ran":5,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unique-unsupervised-image-quality-estimation","title":"UNIQUE: Unsupervised Image Quality Estimation","date":"2018-10-15","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/koniq-10k-towards-an-ecologically-valid-and","title":"KonIQ-10k: Towards an ecologically valid and large-scale IQA database","date":"2018-03-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/nima-neural-image-assessment","title":"NIMA: Neural Image Assessment","date":"2017-09-15","rows_on_this_dataset":2,"code_links":12,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":7,"samples_harvested":32,"samples_ran":21,"samples_unverified":11,"pointer_only_for_licence":17,"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."}