{"url":"/dataset/msu-video-upscalers-quality-enhancement","name":"MSU Video Upscalers: Quality Enhancement","full_name":null,"description_markdown":"The dataset aims to find the algorithms that produce the most visually pleasant image possible and generalize well to a broad range of content. It consists of 30 clips and contains 15 2D-animated segments losslessly recorded from various video games and 15 camera-shot segments from high-bitrate YUV444 sources. The complexity of clips varies significantly in terms of spatial and temporal indexes. Multiple bicubic downscaling mixed with sharpening is used to simulate complex real-world camera degradation. The authors used slight compression and YUV420 conversion to simulate a practical use case. 1920×1080 sources were downscaled to 480×270 input.","description_withheld":null,"homepage":"https://videoprocessing.ai/benchmarks/video-upscalers.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Video Super-Resolution","url":"/task/video-super-resolution","datasets_with_task":"/datasets/task/video-super-resolution"}],"languages":[],"variants":["MSU Video Upscalers: Quality Enhancement"],"data_loaders":[],"num_papers_in_archive":24,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-super-resolution-on-msu-video-upscalers","task":"Video Super-Resolution","dataset_variant":"MSU Video Upscalers: Quality Enhancement","rows":48,"metrics":["LPIPS","SSIM","PSNR","VMAF"],"first_row_in_archive_order":{"model":"BSRGAN","paper":"/paper/designing-a-practical-degradation-model-for","metrics":{"LPIPS":"0.177","PSNR":"29.27","SSIM":"0.836"},"code_links":[{"title":"cszn/BSRGAN","url":"https://github.com/cszn/BSRGAN"},{"title":"pilot7747/sldl","url":"https://github.com/pilot7747/sldl"},{"title":"kadirnar/bsrgan-pip","url":"https://github.com/kadirnar/bsrgan-pip"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/vrt-a-video-restoration-transformer","title":"VRT: A Video Restoration Transformer","date":"2022-01-28","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/investigating-tradeoffs-in-real-world-video","title":"Investigating Tradeoffs in Real-World Video Super-Resolution","date":"2021-11-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/swinir-image-restoration-using-swin","title":"SwinIR: Image Restoration Using Swin Transformer","date":"2021-08-23","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":45,"samples_ran":30,"samples_unverified":15,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/real-esrgan-training-real-world-blind-super","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","date":"2021-07-22","rows_on_this_dataset":6,"code_links":8,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/real-time-super-resolution-system-of-4k-video","title":"Real-Time Super-Resolution System of 4K-Video Based on Deep Learning","date":"2021-07-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/comisr-compression-informed-video-super","title":"COMISR: Compression-Informed Video Super-Resolution","date":"2021-05-04","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/basicvsr-improving-video-super-resolution","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","date":"2021-04-27","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/designing-a-practical-degradation-model-for","title":"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution","date":"2021-03-25","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":12,"samples_ran":8,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dynavsr-dynamic-adaptive-blind-video-super","title":"DynaVSR: Dynamic Adaptive Blind Video Super-Resolution","date":"2020-11-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/local-global-fusion-network-for-video-super","title":"Local-Global Fusion Network for Video Super-Resolution","date":"2020-09-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/iseebetter-spatio-temporal-video-super","title":"iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks","date":"2020-06-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/real-world-super-resolution-via-kernel","title":"Real-World Super-Resolution via Kernel Estimation and Noise Injection","date":"2020-06-19","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deep-blind-video-super-resolution","title":"Deep Blind Video Super-resolution","date":"2020-03-10","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":15,"samples_ran":10,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-video-super-resolution-using-hr-optical","title":"Deep Video Super-Resolution using HR Optical Flow Estimation","date":"2020-01-06","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/temporally-coherent-gans-for-video-super","title":"Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation","date":"2018-11-23","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":25,"samples_ran":2,"samples_unverified":23,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/esrgan-enhanced-super-resolution-generative","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","date":"2018-09-01","rows_on_this_dataset":1,"code_links":46,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":44,"samples_ran":12,"samples_unverified":32,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/frame-recurrent-video-super-resolution","title":"Frame-Recurrent Video Super-Resolution","date":"2018-01-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-a-single-convolutional-super","title":"Learning a Single Convolutional Super-Resolution Network for Multiple Degradations","date":"2017-12-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/image-super-resolution-via-deep-recursive","title":"Image Super-Resolution via Deep Recursive Residual Network","date":"2017-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/detail-revealing-deep-video-super-resolution","title":"Detail-revealing Deep Video Super-resolution","date":"2017-04-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/real-time-video-super-resolution-with-spatio","title":"Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation","date":"2016-11-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/real-time-single-image-and-video-super","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","date":"2016-09-16","rows_on_this_dataset":1,"code_links":47,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":20,"samples_ran":4,"samples_unverified":16,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/accurate-image-super-resolution-using-very","title":"Accurate Image Super-Resolution Using Very Deep Convolutional Networks","date":"2015-11-14","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/image-super-resolution-using-deep","title":"Image Super-Resolution Using Deep Convolutional Networks","date":"2014-12-31","rows_on_this_dataset":1,"code_links":60,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":27,"samples_ran":7,"samples_unverified":20,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":11,"samples_harvested":211,"samples_ran":84,"samples_unverified":127,"pointer_only_for_licence":18,"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."}