{"url":"/sota/video-super-resolution-on-msu-super-1","task":{"name":"Video Super-Resolution","url":"/task/video-super-resolution","note":null},"dataset":{"name":"MSU Super-Resolution for Video Compression","url":"/dataset/msu-super-resolution-for-video-compression"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Video Super-Resolution** is a computer vision task that aims to increase the resolution of a video sequence, typically from lower to higher resolutions. The goal is to generate high-resolution video frames from low-resolution input, improving the overall quality of the video.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Detail-revealing Deep Video Super-Resolution](https://github.com/jiangsutx/SPMC_VideoSR) )</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":["BSQ-rate over Subjective Score","BSQ-rate over ERQA","BSQ-rate over VMAF","BSQ-rate over PSNR","BSQ-rate over MS-SSIM","BSQ-rate over LPIPS"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"BSQ-rate over Subjective Score":"higher","BSQ-rate over ERQA":null,"BSQ-rate over VMAF":null,"BSQ-rate over PSNR":"higher","BSQ-rate over MS-SSIM":"higher","BSQ-rate over LPIPS":null}},"counts":{"rows":85,"rows_with_code":70,"rows_with_paper_page":70,"rows_dated":70,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"RealSR + x264","metrics":{"BSQ-rate over ERQA":"0.77","BSQ-rate over LPIPS":"0.591","BSQ-rate over MS-SSIM":"0.487","BSQ-rate over PSNR":"0.675","BSQ-rate over Subjective Score":"0.196","BSQ-rate over VMAF":"0.775"},"uses_additional_data":false,"paper_date":"2020-06-19","paper":"/paper/real-world-super-resolution-via-kernel","paper_url":"https://ieeexplore.ieee.org/document/9150628","paper_title":"Real-World Super-Resolution via Kernel Estimation and Noise Injection","code":"https://github.com/nihui/realsr-ncnn-vulkan","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"ahq-11 + x264","metrics":{"BSQ-rate over ERQA":"0.883","BSQ-rate over LPIPS":"0.656","BSQ-rate over MS-SSIM":"0.719","BSQ-rate over PSNR":"0.873","BSQ-rate over Subjective Score":"0.271","BSQ-rate over VMAF":"0.753"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"SwinIR + x264","metrics":{"BSQ-rate over ERQA":"0.76","BSQ-rate over LPIPS":"0.559","BSQ-rate over MS-SSIM":"0.736","BSQ-rate over PSNR":"6.268","BSQ-rate over Subjective Score":"0.304","BSQ-rate over VMAF":"0.642"},"uses_additional_data":false,"paper_date":"2021-08-23","paper":"/paper/swinir-image-restoration-using-swin","paper_url":"https://arxiv.org/abs/2108.10257v1","paper_title":"SwinIR: Image Restoration Using Swin Transformer","code":"https://github.com/XPixelGroup/BasicSR","n_code_links":9,"syntology":{"n_ran":30,"n_unverified":15,"n_samples":45,"n_pointer_only_licence":5}},{"rank_in_archive_order":4,"model":"Real-ESRGAN + x264","metrics":{"BSQ-rate over ERQA":"5.58","BSQ-rate over LPIPS":"0.733","BSQ-rate over MS-SSIM":"0.881","BSQ-rate over PSNR":"7.874","BSQ-rate over Subjective Score":"0.335","BSQ-rate over VMAF":"0.698"},"uses_additional_data":false,"paper_date":"2021-07-22","paper":"/paper/real-esrgan-training-real-world-blind-super","paper_url":"https://arxiv.org/abs/2107.10833v2","paper_title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","code":"https://github.com/xinntao/Real-ESRGAN","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"SwinIR + x265","metrics":{"BSQ-rate over ERQA":"1.575","BSQ-rate over LPIPS":"1.474","BSQ-rate over MS-SSIM":"4.641","BSQ-rate over PSNR":"8.13","BSQ-rate over Subjective Score":"0.346","BSQ-rate over VMAF":"1.304"},"uses_additional_data":false,"paper_date":"2021-08-23","paper":"/paper/swinir-image-restoration-using-swin","paper_url":"https://arxiv.org/abs/2108.10257v1","paper_title":"SwinIR: Image Restoration Using Swin Transformer","code":"https://github.com/XPixelGroup/BasicSR","n_code_links":9,"syntology":{"n_ran":30,"n_unverified":15,"n_samples":45,"n_pointer_only_licence":5}},{"rank_in_archive_order":6,"model":"COMISR + x264","metrics":{"BSQ-rate over ERQA":"0.969","BSQ-rate over LPIPS":"1.118","BSQ-rate over MS-SSIM":"0.672","BSQ-rate over PSNR":"6.081","BSQ-rate over Subjective Score":"0.367","BSQ-rate over VMAF":"1.302"},"uses_additional_data":false,"paper_date":"2021-05-04","paper":"/paper/comisr-compression-informed-video-super","paper_url":"https://arxiv.org/abs/2105.01237v2","paper_title":"COMISR: Compression-Informed Video Super-Resolution","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"RealSR + x265","metrics":{"BSQ-rate over ERQA":"1.622","BSQ-rate over LPIPS":"1.206","BSQ-rate over MS-SSIM":"1.033","BSQ-rate over PSNR":"1.064","BSQ-rate over Subjective Score":"0.502","BSQ-rate over VMAF":"1.617"},"uses_additional_data":false,"paper_date":"2020-06-19","paper":"/paper/real-world-super-resolution-via-kernel","paper_url":"https://ieeexplore.ieee.org/document/9150628","paper_title":"Real-World Super-Resolution via Kernel Estimation and Noise Injection","code":"https://github.com/nihui/realsr-ncnn-vulkan","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"RealSR + uavs3e","metrics":{"BSQ-rate over ERQA":"1.943","BSQ-rate over LPIPS":"1.149","BSQ-rate over MS-SSIM":"1.441","BSQ-rate over PSNR":"14.741","BSQ-rate over Subjective Score":"0.639","BSQ-rate over VMAF":"2.253"},"uses_additional_data":false,"paper_date":"2020-06-19","paper":"/paper/real-world-super-resolution-via-kernel","paper_url":"https://ieeexplore.ieee.org/document/9150628","paper_title":"Real-World Super-Resolution via Kernel Estimation and Noise Injection","code":"https://github.com/nihui/realsr-ncnn-vulkan","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"SwinIR + uavs3e","metrics":{"BSQ-rate over ERQA":"6.803","BSQ-rate over LPIPS":"1.671","BSQ-rate over MS-SSIM":"4.411","BSQ-rate over PSNR":"15.144","BSQ-rate over Subjective Score":"0.639","BSQ-rate over VMAF":"1.848"},"uses_additional_data":false,"paper_date":"2021-08-23","paper":"/paper/swinir-image-restoration-using-swin","paper_url":"https://arxiv.org/abs/2108.10257v1","paper_title":"SwinIR: Image Restoration Using Swin Transformer","code":"https://github.com/XPixelGroup/BasicSR","n_code_links":9,"syntology":{"n_ran":30,"n_unverified":15,"n_samples":45,"n_pointer_only_licence":5}},{"rank_in_archive_order":10,"model":"Real-ESRGAN + x265","metrics":{"BSQ-rate over ERQA":"6.328","BSQ-rate over LPIPS":"12.689","BSQ-rate over MS-SSIM":"5.393","BSQ-rate over PSNR":"8.113","BSQ-rate over Subjective Score":"0.64","BSQ-rate over VMAF":"1.464"},"uses_additional_data":false,"paper_date":"2021-07-22","paper":"/paper/real-esrgan-training-real-world-blind-super","paper_url":"https://arxiv.org/abs/2107.10833v2","paper_title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","code":"https://github.com/xinntao/Real-ESRGAN","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"COMISR + vvenc","metrics":{"BSQ-rate over ERQA":"13.246","BSQ-rate over LPIPS":"11.026","BSQ-rate over MS-SSIM":"6.024","BSQ-rate over PSNR":"11.497","BSQ-rate over Subjective Score":"0.701","BSQ-rate over VMAF":"8.105"},"uses_additional_data":false,"paper_date":"2021-05-04","paper":"/paper/comisr-compression-informed-video-super","paper_url":"https://arxiv.org/abs/2105.01237v2","paper_title":"COMISR: Compression-Informed Video Super-Resolution","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"ahq-11 + x265","metrics":{"BSQ-rate over ERQA":"1.917","BSQ-rate over LPIPS":"1.388","BSQ-rate over MS-SSIM":"1.594","BSQ-rate over PSNR":"1.725","BSQ-rate over Subjective Score":"0.724","BSQ-rate over VMAF":"1.503"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"COMISR + x265","metrics":{"BSQ-rate over ERQA":"8.139","BSQ-rate over LPIPS":"12.998","BSQ-rate over MS-SSIM":"4.793","BSQ-rate over PSNR":"10.678","BSQ-rate over Subjective Score":"0.741","BSQ-rate over VMAF":"6.363"},"uses_additional_data":false,"paper_date":"2021-05-04","paper":"/paper/comisr-compression-informed-video-super","paper_url":"https://arxiv.org/abs/2105.01237v2","paper_title":"COMISR: Compression-Informed Video Super-Resolution","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"SwinIR + aomenc","metrics":{"BSQ-rate over ERQA":"10.854","BSQ-rate over LPIPS":"4.566","BSQ-rate over MS-SSIM":"7.105","BSQ-rate over PSNR":"15.144","BSQ-rate over Subjective Score":"0.835","BSQ-rate over VMAF":"3.32"},"uses_additional_data":false,"paper_date":"2021-08-23","paper":"/paper/swinir-image-restoration-using-swin","paper_url":"https://arxiv.org/abs/2108.10257v1","paper_title":"SwinIR: Image Restoration Using Swin Transformer","code":"https://github.com/XPixelGroup/BasicSR","n_code_links":9,"syntology":{"n_ran":30,"n_unverified":15,"n_samples":45,"n_pointer_only_licence":5}},{"rank_in_archive_order":15,"model":"RealSR + aomenc","metrics":{"BSQ-rate over ERQA":"6.762","BSQ-rate over LPIPS":"10.915","BSQ-rate over MS-SSIM":"5.463","BSQ-rate over PSNR":"15.144","BSQ-rate over Subjective Score":"0.843","BSQ-rate over VMAF":"4.283"},"uses_additional_data":false,"paper_date":"2020-06-19","paper":"/paper/real-world-super-resolution-via-kernel","paper_url":"https://ieeexplore.ieee.org/document/9150628","paper_title":"Real-World Super-Resolution via Kernel Estimation and Noise Injection","code":"https://github.com/nihui/realsr-ncnn-vulkan","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"COMISR + uavs3e","metrics":{"BSQ-rate over ERQA":"3.427","BSQ-rate over LPIPS":"3.851","BSQ-rate over MS-SSIM":"7.711","BSQ-rate over PSNR":"5.761","BSQ-rate over Subjective Score":"1.229","BSQ-rate over VMAF":"9.47"},"uses_additional_data":false,"paper_date":"2021-05-04","paper":"/paper/comisr-compression-informed-video-super","paper_url":"https://arxiv.org/abs/2105.01237v2","paper_title":"COMISR: Compression-Informed Video Super-Resolution","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"VRT + x264","metrics":{"BSQ-rate over ERQA":"1.578","BSQ-rate over LPIPS":"1.259","BSQ-rate over MS-SSIM":"0.662","BSQ-rate over PSNR":"1.09","BSQ-rate over Subjective Score":"1.245","BSQ-rate over VMAF":"0.7"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/vrt-a-video-restoration-transformer","paper_url":"https://arxiv.org/abs/2201.12288v2","paper_title":"VRT: A Video Restoration Transformer","code":"https://github.com/jingyunliang/vrt","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":18,"model":"SOF-VSR-BI + x264","metrics":{"BSQ-rate over ERQA":"4.981","BSQ-rate over LPIPS":"1.26","BSQ-rate over MS-SSIM":"0.764","BSQ-rate over PSNR":"6.058","BSQ-rate over Subjective Score":"1.273","BSQ-rate over VMAF":"1.083"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/deep-video-super-resolution-using-hr-optical","paper_url":"https://arxiv.org/abs/2001.02129v1","paper_title":"Deep Video Super-Resolution using HR Optical Flow Estimation","code":"https://github.com/LongguangWang/SOF-VSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":19,"model":"ahq-11 + vvenc","metrics":{"BSQ-rate over ERQA":"2.675","BSQ-rate over LPIPS":"0.981","BSQ-rate over MS-SSIM":"1.575","BSQ-rate over PSNR":"5.761","BSQ-rate over Subjective Score":"1.291","BSQ-rate over VMAF":"0.917"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"SwinIR + vvenc","metrics":{"BSQ-rate over ERQA":"6.624","BSQ-rate over LPIPS":"1.552","BSQ-rate over MS-SSIM":"5.758","BSQ-rate over PSNR":"8.971","BSQ-rate over Subjective Score":"1.35","BSQ-rate over VMAF":"0.887"},"uses_additional_data":false,"paper_date":"2021-08-23","paper":"/paper/swinir-image-restoration-using-swin","paper_url":"https://arxiv.org/abs/2108.10257v1","paper_title":"SwinIR: Image Restoration Using Swin Transformer","code":"https://github.com/XPixelGroup/BasicSR","n_code_links":9,"syntology":{"n_ran":30,"n_unverified":15,"n_samples":45,"n_pointer_only_licence":5}},{"rank_in_archive_order":21,"model":"ahq-11 + uavs3e","metrics":{"BSQ-rate over ERQA":"3.37","BSQ-rate over LPIPS":"1.365","BSQ-rate over MS-SSIM":"3.166","BSQ-rate over PSNR":"5.761","BSQ-rate over Subjective Score":"1.376","BSQ-rate over VMAF":"2.249"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"Real-ESRGAN + aomenc","metrics":{"BSQ-rate over ERQA":"11.584","BSQ-rate over LPIPS":"11.957","BSQ-rate over MS-SSIM":"6.857","BSQ-rate over PSNR":"15.144","BSQ-rate over Subjective Score":"1.398","BSQ-rate over VMAF":"2.712"},"uses_additional_data":false,"paper_date":"2021-07-22","paper":"/paper/real-esrgan-training-real-world-blind-super","paper_url":"https://arxiv.org/abs/2107.10833v2","paper_title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","code":"https://github.com/xinntao/Real-ESRGAN","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"Real-ESRGAN + uavs3e","metrics":{"BSQ-rate over ERQA":"7.225","BSQ-rate over LPIPS":"2.633","BSQ-rate over MS-SSIM":"4.612","BSQ-rate over PSNR":"15.144","BSQ-rate over Subjective Score":"1.417","BSQ-rate over VMAF":"2.122"},"uses_additional_data":false,"paper_date":"2021-07-22","paper":"/paper/real-esrgan-training-real-world-blind-super","paper_url":"https://arxiv.org/abs/2107.10833v2","paper_title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","code":"https://github.com/xinntao/Real-ESRGAN","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"BasicVSR + x264","metrics":{"BSQ-rate over ERQA":"1.659","BSQ-rate over LPIPS":"1.289","BSQ-rate over MS-SSIM":"0.751","BSQ-rate over PSNR":"1.212","BSQ-rate over Subjective Score":"1.49","BSQ-rate over VMAF":"0.714"},"uses_additional_data":false,"paper_date":"2020-12-03","paper":"/paper/basicvsr-the-search-for-essential-components","paper_url":"https://arxiv.org/abs/2012.02181v2","paper_title":"BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond","code":"https://github.com/XPixelGroup/BasicSR","n_code_links":6,"syntology":null},{"rank_in_archive_order":25,"model":"RBPN + x264","metrics":{"BSQ-rate over ERQA":"1.599","BSQ-rate over LPIPS":"1.335","BSQ-rate over MS-SSIM":"0.729","BSQ-rate over PSNR":"1.127","BSQ-rate over Subjective Score":"1.498","BSQ-rate over VMAF":"0.733"},"uses_additional_data":false,"paper_date":"2019-03-25","paper":"/paper/recurrent-back-projection-network-for-video","paper_url":"http://arxiv.org/abs/1903.10128v1","paper_title":"Recurrent Back-Projection Network for Video Super-Resolution","code":"https://github.com/alterzero/RBPN-PyTorch","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"COMISR + aomenc","metrics":{"BSQ-rate over ERQA":"11.177","BSQ-rate over LPIPS":"4.801","BSQ-rate over MS-SSIM":"11.303","BSQ-rate over PSNR":"15.144","BSQ-rate over Subjective Score":"1.943","BSQ-rate over VMAF":"10.67"},"uses_additional_data":false,"paper_date":"2021-05-04","paper":"/paper/comisr-compression-informed-video-super","paper_url":"https://arxiv.org/abs/2105.01237v2","paper_title":"COMISR: Compression-Informed Video Super-Resolution","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"ahq-11 + aomenc","metrics":{"BSQ-rate over ERQA":"4.799","BSQ-rate over LPIPS":"1.368","BSQ-rate over MS-SSIM":"5.999","BSQ-rate over PSNR":"12.542","BSQ-rate over Subjective Score":"1.95","BSQ-rate over VMAF":"2.808"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"VRT + x265","metrics":{"BSQ-rate over ERQA":"8.92","BSQ-rate over LPIPS":"11.329","BSQ-rate over MS-SSIM":"1.257","BSQ-rate over PSNR":"6.634","BSQ-rate over Subjective Score":"2.023","BSQ-rate over VMAF":"1.217"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/vrt-a-video-restoration-transformer","paper_url":"https://arxiv.org/abs/2201.12288v2","paper_title":"VRT: A Video Restoration Transformer","code":"https://github.com/jingyunliang/vrt","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":29,"model":"VRT + vvenc","metrics":{"BSQ-rate over ERQA":"18.333","BSQ-rate over LPIPS":"11.496","BSQ-rate over MS-SSIM":"0.836","BSQ-rate over PSNR":"5.777","BSQ-rate over Subjective Score":"2.235","BSQ-rate over VMAF":"0.652"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/vrt-a-video-restoration-transformer","paper_url":"https://arxiv.org/abs/2201.12288v2","paper_title":"VRT: A Video Restoration Transformer","code":"https://github.com/jingyunliang/vrt","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":30,"model":"BasicVSR + x265","metrics":{"BSQ-rate over ERQA":"8.921","BSQ-rate over LPIPS":"13.198","BSQ-rate over MS-SSIM":"1.48","BSQ-rate over PSNR":"1.906","BSQ-rate over Subjective Score":"2.238","BSQ-rate over VMAF":"1.272"},"uses_additional_data":false,"paper_date":"2020-12-03","paper":"/paper/basicvsr-the-search-for-essential-components","paper_url":"https://arxiv.org/abs/2012.02181v2","paper_title":"BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond","code":"https://github.com/XPixelGroup/BasicSR","n_code_links":6,"syntology":null},{"rank_in_archive_order":31,"model":"SOF-VSR-BI + x265","metrics":{"BSQ-rate over ERQA":"18.545","BSQ-rate over LPIPS":"11.236","BSQ-rate over MS-SSIM":"4.558","BSQ-rate over PSNR":"9.07","BSQ-rate over Subjective Score":"2.244","BSQ-rate over VMAF":"3.565"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/deep-video-super-resolution-using-hr-optical","paper_url":"https://arxiv.org/abs/2001.02129v1","paper_title":"Deep Video Super-Resolution using HR Optical Flow Estimation","code":"https://github.com/LongguangWang/SOF-VSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":32,"model":"RBPN + x265","metrics":{"BSQ-rate over ERQA":"13.185","BSQ-rate over LPIPS":"13.237","BSQ-rate over MS-SSIM":"1.438","BSQ-rate over PSNR":"1.89","BSQ-rate over Subjective Score":"2.282","BSQ-rate over VMAF":"1.324"},"uses_additional_data":false,"paper_date":"2019-03-25","paper":"/paper/recurrent-back-projection-network-for-video","paper_url":"http://arxiv.org/abs/1903.10128v1","paper_title":"Recurrent Back-Projection Network for Video Super-Resolution","code":"https://github.com/alterzero/RBPN-PyTorch","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"VRT + uavs3e","metrics":{"BSQ-rate over ERQA":"6.619","BSQ-rate over LPIPS":"4.003","BSQ-rate over MS-SSIM":"1.982","BSQ-rate over PSNR":"5.862","BSQ-rate over Subjective Score":"2.511","BSQ-rate over VMAF":"1.425"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/vrt-a-video-restoration-transformer","paper_url":"https://arxiv.org/abs/2201.12288v2","paper_title":"VRT: A Video Restoration Transformer","code":"https://github.com/jingyunliang/vrt","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":34,"model":"VRT + aomenc","metrics":{"BSQ-rate over ERQA":"12.289","BSQ-rate over LPIPS":"4.429","BSQ-rate over MS-SSIM":"2.797","BSQ-rate over PSNR":"10.075","BSQ-rate over Subjective Score":"2.631","BSQ-rate over VMAF":"1.733"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/vrt-a-video-restoration-transformer","paper_url":"https://arxiv.org/abs/2201.12288v2","paper_title":"VRT: A Video Restoration Transformer","code":"https://github.com/jingyunliang/vrt","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":35,"model":"BasicVSR + vvenc","metrics":{"BSQ-rate over ERQA":"18.333","BSQ-rate over LPIPS":"11.561","BSQ-rate over MS-SSIM":"0.919","BSQ-rate over PSNR":"5.781","BSQ-rate over Subjective Score":"2.659","BSQ-rate over VMAF":"0.676"},"uses_additional_data":false,"paper_date":"2020-12-03","paper":"/paper/basicvsr-the-search-for-essential-components","paper_url":"https://arxiv.org/abs/2012.02181v2","paper_title":"BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond","code":"https://github.com/XPixelGroup/BasicSR","n_code_links":6,"syntology":null},{"rank_in_archive_order":36,"model":"BasicVSR + aomenc","metrics":{"BSQ-rate over ERQA":"14.568","BSQ-rate over LPIPS":"4.938","BSQ-rate over MS-SSIM":"4.128","BSQ-rate over PSNR":"11.428","BSQ-rate over Subjective Score":"2.673","BSQ-rate over VMAF":"1.857"},"uses_additional_data":false,"paper_date":"2020-12-03","paper":"/paper/basicvsr-the-search-for-essential-components","paper_url":"https://arxiv.org/abs/2012.02181v2","paper_title":"BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond","code":"https://github.com/XPixelGroup/BasicSR","n_code_links":6,"syntology":null},{"rank_in_archive_order":37,"model":"RBPN + aomenc","metrics":{"BSQ-rate over ERQA":"13.572","BSQ-rate over LPIPS":"5.821","BSQ-rate over MS-SSIM":"3.089","BSQ-rate over PSNR":"10.89","BSQ-rate over Subjective Score":"2.7","BSQ-rate over VMAF":"1.996"},"uses_additional_data":false,"paper_date":"2019-03-25","paper":"/paper/recurrent-back-projection-network-for-video","paper_url":"http://arxiv.org/abs/1903.10128v1","paper_title":"Recurrent Back-Projection Network for Video Super-Resolution","code":"https://github.com/alterzero/RBPN-PyTorch","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"RBPN + vvenc","metrics":{"BSQ-rate over ERQA":"18.314","BSQ-rate over LPIPS":"11.777","BSQ-rate over MS-SSIM":"0.884","BSQ-rate over PSNR":"5.783","BSQ-rate over Subjective Score":"2.719","BSQ-rate over VMAF":"0.689"},"uses_additional_data":false,"paper_date":"2019-03-25","paper":"/paper/recurrent-back-projection-network-for-video","paper_url":"http://arxiv.org/abs/1903.10128v1","paper_title":"Recurrent Back-Projection Network for Video Super-Resolution","code":"https://github.com/alterzero/RBPN-PyTorch","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"BasicVSR + uavs3e","metrics":{"BSQ-rate over ERQA":"8.251","BSQ-rate over LPIPS":"4.383","BSQ-rate over MS-SSIM":"2.261","BSQ-rate over PSNR":"6.833","BSQ-rate over Subjective Score":"2.724","BSQ-rate over VMAF":"1.523"},"uses_additional_data":false,"paper_date":"2020-12-03","paper":"/paper/basicvsr-the-search-for-essential-components","paper_url":"https://arxiv.org/abs/2012.02181v2","paper_title":"BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond","code":"https://github.com/XPixelGroup/BasicSR","n_code_links":6,"syntology":null},{"rank_in_archive_order":40,"model":"SOF-VSR-BI + vvenc","metrics":{"BSQ-rate over ERQA":"18.844","BSQ-rate over LPIPS":"11.273","BSQ-rate over MS-SSIM":"4.882","BSQ-rate over PSNR":"9.245","BSQ-rate over Subjective Score":"2.822","BSQ-rate over VMAF":"4.527"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/deep-video-super-resolution-using-hr-optical","paper_url":"https://arxiv.org/abs/2001.02129v1","paper_title":"Deep Video Super-Resolution using HR Optical Flow Estimation","code":"https://github.com/LongguangWang/SOF-VSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":41,"model":"SOF-VSR-BI + aomenc","metrics":{"BSQ-rate over ERQA":"12.808","BSQ-rate over LPIPS":"4.82","BSQ-rate over MS-SSIM":"6.833","BSQ-rate over PSNR":"11.314","BSQ-rate over Subjective Score":"2.84","BSQ-rate over VMAF":"5.398"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/deep-video-super-resolution-using-hr-optical","paper_url":"https://arxiv.org/abs/2001.02129v1","paper_title":"Deep Video Super-Resolution using HR Optical Flow Estimation","code":"https://github.com/LongguangWang/SOF-VSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":42,"model":"DBVSR + vvenc","metrics":{"BSQ-rate over ERQA":"15.988","BSQ-rate over LPIPS":"11.435","BSQ-rate over MS-SSIM":"0.898","BSQ-rate over PSNR":"5.765","BSQ-rate over Subjective Score":"2.842","BSQ-rate over VMAF":"0.698"},"uses_additional_data":false,"paper_date":"2020-03-10","paper":"/paper/deep-blind-video-super-resolution","paper_url":"https://arxiv.org/abs/2003.04716v1","paper_title":"Deep Blind Video Super-resolution","code":"https://github.com/csbhr/Deep-Blind-VSR","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":43,"model":"RBPN + uavs3e","metrics":{"BSQ-rate over ERQA":"7.133","BSQ-rate over LPIPS":"4.859","BSQ-rate over MS-SSIM":"2.263","BSQ-rate over PSNR":"6.301","BSQ-rate over Subjective Score":"2.944","BSQ-rate over VMAF":"0.702"},"uses_additional_data":false,"paper_date":"2019-03-25","paper":"/paper/recurrent-back-projection-network-for-video","paper_url":"http://arxiv.org/abs/1903.10128v1","paper_title":"Recurrent Back-Projection Network for Video Super-Resolution","code":"https://github.com/alterzero/RBPN-PyTorch","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":44,"model":"LGFN + vvenc","metrics":{"BSQ-rate over ERQA":"18.342","BSQ-rate over LPIPS":"11.759","BSQ-rate over MS-SSIM":"0.889","BSQ-rate over PSNR":"5.768","BSQ-rate over Subjective Score":"2.944","BSQ-rate over VMAF":"1.626"},"uses_additional_data":false,"paper_date":"2020-09-22","paper":"/paper/local-global-fusion-network-for-video-super","paper_url":"https://ieeexplore.ieee.org/document/9203860/authors#authors","paper_title":"Local-Global Fusion Network for Video Super-Resolution","code":"https://github.com/BIOINSu/LGFN","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"SOF-VSR-BI + uavs3e","metrics":{"BSQ-rate over ERQA":"5.299","BSQ-rate over LPIPS":"4.23","BSQ-rate over MS-SSIM":"6.82","BSQ-rate over PSNR":"10.917","BSQ-rate over Subjective Score":"3.196","BSQ-rate over VMAF":"5.361"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/deep-video-super-resolution-using-hr-optical","paper_url":"https://arxiv.org/abs/2001.02129v1","paper_title":"Deep Video Super-Resolution using HR Optical Flow Estimation","code":"https://github.com/LongguangWang/SOF-VSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":46,"model":"amq-12 + x264","metrics":{"BSQ-rate over ERQA":"0.922","BSQ-rate over LPIPS":"0.767","BSQ-rate over MS-SSIM":"0.643","BSQ-rate over PSNR":"0.813"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":47,"model":"SOF-VSR-BD + x264","metrics":{"BSQ-rate over ERQA":"1.544","BSQ-rate over LPIPS":"1.262","BSQ-rate over MS-SSIM":"0.843","BSQ-rate over PSNR":"2.763","BSQ-rate over VMAF":"1.213"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/deep-video-super-resolution-using-hr-optical","paper_url":"https://arxiv.org/abs/2001.02129v1","paper_title":"Deep Video Super-Resolution using HR Optical Flow Estimation","code":"https://github.com/LongguangWang/SOF-VSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":48,"model":"DBVSR + x264","metrics":{"BSQ-rate over ERQA":"1.606","BSQ-rate over LPIPS":"1.293","BSQ-rate over MS-SSIM":"0.714","BSQ-rate over PSNR":"1.082","BSQ-rate over VMAF":"0.75"},"uses_additional_data":false,"paper_date":"2020-03-10","paper":"/paper/deep-blind-video-super-resolution","paper_url":"https://arxiv.org/abs/2003.04716v1","paper_title":"Deep Blind Video Super-resolution","code":"https://github.com/csbhr/Deep-Blind-VSR","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":49,"model":"LGFN + x264","metrics":{"BSQ-rate over ERQA":"1.704","BSQ-rate over LPIPS":"1.324","BSQ-rate over MS-SSIM":"0.77","BSQ-rate over PSNR":"1.151","BSQ-rate over VMAF":"0.744"},"uses_additional_data":false,"paper_date":"2020-09-22","paper":"/paper/local-global-fusion-network-for-video-super","paper_url":"https://ieeexplore.ieee.org/document/9203860/authors#authors","paper_title":"Local-Global Fusion Network for Video Super-Resolution","code":"https://github.com/BIOINSu/LGFN","n_code_links":1,"syntology":null},{"rank_in_archive_order":50,"model":"TMNet + x264","metrics":{"BSQ-rate over ERQA":"1.879","BSQ-rate over LPIPS":"1.377","BSQ-rate over MS-SSIM":"0.844","BSQ-rate over PSNR":"1.481","BSQ-rate over VMAF":"1.061"},"uses_additional_data":false,"paper_date":"2021-04-21","paper":"/paper/temporal-modulation-network-for-controllable","paper_url":"https://arxiv.org/abs/2104.10642v2","paper_title":"Temporal Modulation Network for Controllable Space-Time Video Super-Resolution","code":"https://github.com/CS-GangXu/TMNet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":51,"model":"amq-12 + x265","metrics":{"BSQ-rate over ERQA":"1.996","BSQ-rate over LPIPS":"10.639","BSQ-rate over MS-SSIM":"1.462","BSQ-rate over PSNR":"1.629","BSQ-rate over VMAF":"1.525"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":52,"model":"bicubic + x264","metrics":{"BSQ-rate over ERQA":"2.182","BSQ-rate over LPIPS":"10.965","BSQ-rate over MS-SSIM":"0.699","BSQ-rate over PSNR":"0.91","BSQ-rate over VMAF":"1.338"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":53,"model":"amq-12 + uavs3e","metrics":{"BSQ-rate over ERQA":"3.679","BSQ-rate over LPIPS":"1.742","BSQ-rate over MS-SSIM":"2.861","BSQ-rate over PSNR":"6.547","BSQ-rate over VMAF":"2.308"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":54,"model":"EGVSR + x264","metrics":{"BSQ-rate over ERQA":"6.029","BSQ-rate over LPIPS":"1.226","BSQ-rate over MS-SSIM":"1.196","BSQ-rate over PSNR":"10.595","BSQ-rate over VMAF":"1.519"},"uses_additional_data":false,"paper_date":"2021-07-12","paper":"/paper/real-time-super-resolution-system-of-4k-video","paper_url":"https://arxiv.org/abs/2107.05307v2","paper_title":"Real-Time Super-Resolution System of 4K-Video Based on Deep Learning","code":"https://github.com/Thmen/EGVSR","n_code_links":1,"syntology":null},{"rank_in_archive_order":55,"model":"RSDN + x264","metrics":{"BSQ-rate over ERQA":"6.58","BSQ-rate over LPIPS":"10.775","BSQ-rate over MS-SSIM":"1.023","BSQ-rate over PSNR":"13.348","BSQ-rate over VMAF":"1.5"},"uses_additional_data":false,"paper_date":"2020-08-02","paper":"/paper/video-super-resolution-with-recurrent","paper_url":"https://arxiv.org/abs/2008.00455v1","paper_title":"Video Super-Resolution with Recurrent Structure-Detail Network","code":"https://github.com/junpan19/RSDN","n_code_links":2,"syntology":null},{"rank_in_archive_order":56,"model":"Real-ESRGAN + vvenc","metrics":{"BSQ-rate over ERQA":"6.712","BSQ-rate over LPIPS":"12.744","BSQ-rate over MS-SSIM":"5.95","BSQ-rate over PSNR":"14.561","BSQ-rate over VMAF":"3.8"},"uses_additional_data":false,"paper_date":"2021-07-22","paper":"/paper/real-esrgan-training-real-world-blind-super","paper_url":"https://arxiv.org/abs/2107.10833v2","paper_title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","code":"https://github.com/xinntao/Real-ESRGAN","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":57,"model":"DBVSR + uavs3e","metrics":{"BSQ-rate over ERQA":"7.0","BSQ-rate over LPIPS":"4.371","BSQ-rate over MS-SSIM":"2.396","BSQ-rate over PSNR":"5.845","BSQ-rate over VMAF":"1.83"},"uses_additional_data":false,"paper_date":"2020-03-10","paper":"/paper/deep-blind-video-super-resolution","paper_url":"https://arxiv.org/abs/2003.04716v1","paper_title":"Deep Blind Video Super-resolution","code":"https://github.com/csbhr/Deep-Blind-VSR","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":58,"model":"LGFN + uavs3e","metrics":{"BSQ-rate over ERQA":"9.279","BSQ-rate over LPIPS":"4.504","BSQ-rate over MS-SSIM":"2.427","BSQ-rate over PSNR":"5.503","BSQ-rate over VMAF":"1.625"},"uses_additional_data":false,"paper_date":"2020-09-22","paper":"/paper/local-global-fusion-network-for-video-super","paper_url":"https://ieeexplore.ieee.org/document/9203860/authors#authors","paper_title":"Local-Global Fusion Network for Video Super-Resolution","code":"https://github.com/BIOINSu/LGFN","n_code_links":1,"syntology":null},{"rank_in_archive_order":59,"model":"EGVSR + uavs3e","metrics":{"BSQ-rate over ERQA":"10.1","BSQ-rate over LPIPS":"4.0","BSQ-rate over MS-SSIM":"8.194","BSQ-rate over PSNR":"15.144","BSQ-rate over VMAF":"10.337"},"uses_additional_data":false,"paper_date":"2021-07-12","paper":"/paper/real-time-super-resolution-system-of-4k-video","paper_url":"https://arxiv.org/abs/2107.05307v2","paper_title":"Real-Time Super-Resolution System of 4K-Video Based on Deep Learning","code":"https://github.com/Thmen/EGVSR","n_code_links":1,"syntology":null},{"rank_in_archive_order":60,"model":"amq-12 + aomenc","metrics":{"BSQ-rate over ERQA":"10.388","BSQ-rate over LPIPS":"1.843","BSQ-rate over MS-SSIM":"5.883","BSQ-rate over PSNR":"11.079","BSQ-rate over VMAF":"2.874"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":61,"model":"amq-12 + vvenc","metrics":{"BSQ-rate over ERQA":"11.064","BSQ-rate over LPIPS":"1.219","BSQ-rate over MS-SSIM":"1.371","BSQ-rate over PSNR":"5.718","BSQ-rate over VMAF":"0.898"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":62,"model":"SOF-VSR-BD + uavs3e","metrics":{"BSQ-rate over ERQA":"11.458","BSQ-rate over LPIPS":"4.007","BSQ-rate over MS-SSIM":"3.566","BSQ-rate over PSNR":"8.658","BSQ-rate over VMAF":"6.596"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/deep-video-super-resolution-using-hr-optical","paper_url":"https://arxiv.org/abs/2001.02129v1","paper_title":"Deep Video Super-Resolution using HR Optical Flow Estimation","code":"https://github.com/LongguangWang/SOF-VSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":63,"model":"EGVSR + x265","metrics":{"BSQ-rate over ERQA":"12.917","BSQ-rate over LPIPS":"10.748","BSQ-rate over MS-SSIM":"5.548","BSQ-rate over PSNR":"10.701","BSQ-rate over VMAF":"6.497"},"uses_additional_data":false,"paper_date":"2021-07-12","paper":"/paper/real-time-super-resolution-system-of-4k-video","paper_url":"https://arxiv.org/abs/2107.05307v2","paper_title":"Real-Time Super-Resolution System of 4K-Video Based on Deep Learning","code":"https://github.com/Thmen/EGVSR","n_code_links":1,"syntology":null},{"rank_in_archive_order":64,"model":"SOF-VSR-BD + x265","metrics":{"BSQ-rate over ERQA":"13.098","BSQ-rate over LPIPS":"13.141","BSQ-rate over MS-SSIM":"1.825","BSQ-rate over PSNR":"3.274","BSQ-rate over VMAF":"4.346"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/deep-video-super-resolution-using-hr-optical","paper_url":"https://arxiv.org/abs/2001.02129v1","paper_title":"Deep Video Super-Resolution using HR Optical Flow Estimation","code":"https://github.com/LongguangWang/SOF-VSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":65,"model":"DBVSR + x265","metrics":{"BSQ-rate over ERQA":"13.145","BSQ-rate over LPIPS":"13.211","BSQ-rate over MS-SSIM":"1.438","BSQ-rate over PSNR":"6.607","BSQ-rate over VMAF":"1.383"},"uses_additional_data":false,"paper_date":"2020-03-10","paper":"/paper/deep-blind-video-super-resolution","paper_url":"https://arxiv.org/abs/2003.04716v1","paper_title":"Deep Blind Video Super-resolution","code":"https://github.com/csbhr/Deep-Blind-VSR","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":66,"model":"TMNet + uavs3e","metrics":{"BSQ-rate over ERQA":"13.187","BSQ-rate over LPIPS":"5.015","BSQ-rate over MS-SSIM":"4.317","BSQ-rate over PSNR":"15.144","BSQ-rate over VMAF":"3.487"},"uses_additional_data":false,"paper_date":"2021-04-21","paper":"/paper/temporal-modulation-network-for-controllable","paper_url":"https://arxiv.org/abs/2104.10642v2","paper_title":"Temporal Modulation Network for Controllable Space-Time Video Super-Resolution","code":"https://github.com/CS-GangXu/TMNet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":67,"model":"LGFN + x265","metrics":{"BSQ-rate over ERQA":"13.213","BSQ-rate over LPIPS":"11.399","BSQ-rate over MS-SSIM":"1.533","BSQ-rate over PSNR":"6.646","BSQ-rate over VMAF":"1.341"},"uses_additional_data":false,"paper_date":"2020-09-22","paper":"/paper/local-global-fusion-network-for-video-super","paper_url":"https://ieeexplore.ieee.org/document/9203860/authors#authors","paper_title":"Local-Global Fusion Network for Video Super-Resolution","code":"https://github.com/BIOINSu/LGFN","n_code_links":1,"syntology":null},{"rank_in_archive_order":68,"model":"RSDN + x265","metrics":{"BSQ-rate over ERQA":"13.416","BSQ-rate over LPIPS":"13.232","BSQ-rate over MS-SSIM":"5.682","BSQ-rate over PSNR":"13.403","BSQ-rate over VMAF":"6.467"},"uses_additional_data":false,"paper_date":"2020-08-02","paper":"/paper/video-super-resolution-with-recurrent","paper_url":"https://arxiv.org/abs/2008.00455v1","paper_title":"Video Super-Resolution with Recurrent Structure-Detail Network","code":"https://github.com/junpan19/RSDN","n_code_links":2,"syntology":null},{"rank_in_archive_order":69,"model":"DBVSR + aomenc","metrics":{"BSQ-rate over ERQA":"13.476","BSQ-rate over LPIPS":"4.916","BSQ-rate over MS-SSIM":"3.886","BSQ-rate over PSNR":"10.296","BSQ-rate over VMAF":"2.093"},"uses_additional_data":false,"paper_date":"2020-03-10","paper":"/paper/deep-blind-video-super-resolution","paper_url":"https://arxiv.org/abs/2003.04716v1","paper_title":"Deep Blind Video Super-resolution","code":"https://github.com/csbhr/Deep-Blind-VSR","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":70,"model":"TMNet + x265","metrics":{"BSQ-rate over ERQA":"13.577","BSQ-rate over LPIPS":"13.485","BSQ-rate over MS-SSIM":"1.735","BSQ-rate over PSNR":"7.046","BSQ-rate over VMAF":"2.009"},"uses_additional_data":false,"paper_date":"2021-04-21","paper":"/paper/temporal-modulation-network-for-controllable","paper_url":"https://arxiv.org/abs/2104.10642v2","paper_title":"Temporal Modulation Network for Controllable Space-Time Video Super-Resolution","code":"https://github.com/CS-GangXu/TMNet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":71,"model":"EGVSR + vvenc","metrics":{"BSQ-rate over ERQA":"13.684","BSQ-rate over LPIPS":"10.643","BSQ-rate over MS-SSIM":"6.209","BSQ-rate over PSNR":"11.543","BSQ-rate over VMAF":"10.163"},"uses_additional_data":false,"paper_date":"2021-07-12","paper":"/paper/real-time-super-resolution-system-of-4k-video","paper_url":"https://arxiv.org/abs/2107.05307v2","paper_title":"Real-Time Super-Resolution System of 4K-Video Based on Deep Learning","code":"https://github.com/Thmen/EGVSR","n_code_links":1,"syntology":null},{"rank_in_archive_order":72,"model":"LGFN + aomenc","metrics":{"BSQ-rate over ERQA":"14.631","BSQ-rate over LPIPS":"5.536","BSQ-rate over MS-SSIM":"4.321","BSQ-rate over PSNR":"9.79","BSQ-rate over VMAF":"1.99"},"uses_additional_data":false,"paper_date":"2020-09-22","paper":"/paper/local-global-fusion-network-for-video-super","paper_url":"https://ieeexplore.ieee.org/document/9203860/authors#authors","paper_title":"Local-Global Fusion Network for Video Super-Resolution","code":"https://github.com/BIOINSu/LGFN","n_code_links":1,"syntology":null},{"rank_in_archive_order":73,"model":"RSDN + vvenc","metrics":{"BSQ-rate over ERQA":"14.95","BSQ-rate over LPIPS":"4.866","BSQ-rate over MS-SSIM":"9.138","BSQ-rate over PSNR":"14.061","BSQ-rate over VMAF":"10.145"},"uses_additional_data":false,"paper_date":"2020-08-02","paper":"/paper/video-super-resolution-with-recurrent","paper_url":"https://arxiv.org/abs/2008.00455v1","paper_title":"Video Super-Resolution with Recurrent Structure-Detail Network","code":"https://github.com/junpan19/RSDN","n_code_links":2,"syntology":null},{"rank_in_archive_order":74,"model":"SOF-VSR-BD + aomenc","metrics":{"BSQ-rate over ERQA":"15.11","BSQ-rate over LPIPS":"4.034","BSQ-rate over MS-SSIM":"7.546","BSQ-rate over PSNR":"13.076","BSQ-rate over VMAF":"7.464"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/deep-video-super-resolution-using-hr-optical","paper_url":"https://arxiv.org/abs/2001.02129v1","paper_title":"Deep Video Super-Resolution using HR Optical Flow Estimation","code":"https://github.com/LongguangWang/SOF-VSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":75,"model":"SOF-VSR-BD + vvenc","metrics":{"BSQ-rate over ERQA":"15.958","BSQ-rate over LPIPS":"13.494","BSQ-rate over MS-SSIM":"2.112","BSQ-rate over PSNR":"8.027","BSQ-rate over VMAF":"6.41"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/deep-video-super-resolution-using-hr-optical","paper_url":"https://arxiv.org/abs/2001.02129v1","paper_title":"Deep Video Super-Resolution using HR Optical Flow Estimation","code":"https://github.com/LongguangWang/SOF-VSR","n_code_links":2,"syntology":null},{"rank_in_archive_order":76,"model":"bicubic + x265","metrics":{"BSQ-rate over ERQA":"16.014","BSQ-rate over LPIPS":"15.363","BSQ-rate over MS-SSIM":"4.563","BSQ-rate over PSNR":"6.473","BSQ-rate over VMAF":"6.469"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":77,"model":"EGVSR + aomenc","metrics":{"BSQ-rate over ERQA":"16.733","BSQ-rate over LPIPS":"5.67","BSQ-rate over MS-SSIM":"11.643","BSQ-rate over PSNR":"15.144","BSQ-rate over VMAF":"10.67"},"uses_additional_data":false,"paper_date":"2021-07-12","paper":"/paper/real-time-super-resolution-system-of-4k-video","paper_url":"https://arxiv.org/abs/2107.05307v2","paper_title":"Real-Time Super-Resolution System of 4K-Video Based on Deep Learning","code":"https://github.com/Thmen/EGVSR","n_code_links":1,"syntology":null},{"rank_in_archive_order":78,"model":"RSDN + uavs3e","metrics":{"BSQ-rate over ERQA":"18.327","BSQ-rate over LPIPS":"13.844","BSQ-rate over MS-SSIM":"11.643","BSQ-rate over PSNR":"15.144","BSQ-rate over VMAF":"9.796"},"uses_additional_data":false,"paper_date":"2020-08-02","paper":"/paper/video-super-resolution-with-recurrent","paper_url":"https://arxiv.org/abs/2008.00455v1","paper_title":"Video Super-Resolution with Recurrent Structure-Detail Network","code":"https://github.com/junpan19/RSDN","n_code_links":2,"syntology":null},{"rank_in_archive_order":79,"model":"RSDN + aomenc","metrics":{"BSQ-rate over ERQA":"20.617","BSQ-rate over LPIPS":"14.574","BSQ-rate over MS-SSIM":"11.643","BSQ-rate over PSNR":"15.144","BSQ-rate over VMAF":"10.67"},"uses_additional_data":false,"paper_date":"2020-08-02","paper":"/paper/video-super-resolution-with-recurrent","paper_url":"https://arxiv.org/abs/2008.00455v1","paper_title":"Video Super-Resolution with Recurrent Structure-Detail Network","code":"https://github.com/junpan19/RSDN","n_code_links":2,"syntology":null},{"rank_in_archive_order":80,"model":"TMNet + vvenc","metrics":{"BSQ-rate over ERQA":"21.303","BSQ-rate over LPIPS":"13.988","BSQ-rate over MS-SSIM":"1.813","BSQ-rate over PSNR":"9.43","BSQ-rate over VMAF":"1.795"},"uses_additional_data":false,"paper_date":"2021-04-21","paper":"/paper/temporal-modulation-network-for-controllable","paper_url":"https://arxiv.org/abs/2104.10642v2","paper_title":"Temporal Modulation Network for Controllable Space-Time Video Super-Resolution","code":"https://github.com/CS-GangXu/TMNet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":81,"model":"TMNet + aomenc","metrics":{"BSQ-rate over ERQA":"21.798","BSQ-rate over LPIPS":"6.276","BSQ-rate over MS-SSIM":"10.322","BSQ-rate over PSNR":"15.144","BSQ-rate over VMAF":"4.667"},"uses_additional_data":false,"paper_date":"2021-04-21","paper":"/paper/temporal-modulation-network-for-controllable","paper_url":"https://arxiv.org/abs/2104.10642v2","paper_title":"Temporal Modulation Network for Controllable Space-Time Video Super-Resolution","code":"https://github.com/CS-GangXu/TMNet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":82,"model":"bicubic + aomenc","metrics":{"BSQ-rate over ERQA":"21.965","BSQ-rate over LPIPS":"17.458","BSQ-rate over MS-SSIM":"2.888","BSQ-rate over PSNR":"8.395","BSQ-rate over VMAF":"6.797"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":83,"model":"bicubic + uavs3e","metrics":{"BSQ-rate over ERQA":"21.965","BSQ-rate over LPIPS":"18.057","BSQ-rate over MS-SSIM":"5.068","BSQ-rate over PSNR":"7.372","BSQ-rate over VMAF":"7.026"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":84,"model":"bicubic + vvenc","metrics":{"BSQ-rate over ERQA":"21.965","BSQ-rate over LPIPS":"16.894","BSQ-rate over MS-SSIM":"5.735","BSQ-rate over PSNR":"12.787","BSQ-rate over VMAF":"8.635"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":85,"model":"RealSR + vvenc","metrics":{"BSQ-rate over ERQA":"21.965","BSQ-rate over LPIPS":"18.344","BSQ-rate over MS-SSIM":"11.643","BSQ-rate over PSNR":"15.144","BSQ-rate over VMAF":"10.67"},"uses_additional_data":false,"paper_date":"2020-06-19","paper":"/paper/real-world-super-resolution-via-kernel","paper_url":"https://ieeexplore.ieee.org/document/9150628","paper_title":"Real-World Super-Resolution via Kernel Estimation and Noise Injection","code":"https://github.com/nihui/realsr-ncnn-vulkan","n_code_links":2,"syntology":null}],"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":35,"rows_with_any_sample_ran":25,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":47,"n_unverified":43,"n_samples":90,"n_pointer_only_licence":10,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":235,"n_unverified":215,"n_samples":450,"n_pointer_only_licence":50,"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"}}}