{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/video-super-resolution-with-recurrent","title":"Video Super-Resolution with Recurrent Structure-Detail Network","arxiv_id":"2008.00455","date":"2020-08-02","proceeding":"ECCV 2020 8","authors":["Takashi Isobe","Xu Jia","Shuhang Gu","Songjiang Li","Shengjin Wang","Qi Tian"],"abstract":"Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window. They are less efficient compared to the recurrent-based methods. In this work, we propose a novel recurrent video super-resolution method which is both effective and efficient in exploiting previous frames to super-resolve the current frame. It divides the input into structure and detail components which are fed to a recurrent unit composed of several proposed two-stream structure-detail blocks. In addition, a hidden state adaptation module that allows the current frame to selectively use information from hidden state is introduced to enhance its robustness to appearance change and error accumulation. Extensive ablation study validate the effectiveness of the proposed modules. Experiments on several benchmark datasets demonstrate the superior performance of the proposed method compared to state-of-the-art methods on video super-resolution.","url_abs":"https://arxiv.org/abs/2008.00455v1","url_pdf":"https://arxiv.org/pdf/2008.00455v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"video-super-resolution-with-recurrent","repo_url":"https://github.com/junpan19/RSDN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"video-super-resolution-with-recurrent","repo_url":"https://github.com/Feynman1999/MgeEditing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"video-super-resolution","task_name":"Video Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-super-resolution-on-msu-super-1","task":"Video Super-Resolution","dataset":"MSU Super-Resolution for Video Compression","model":"RSDN + x264","rank_in_archive_order":55,"of":85,"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},{"leaderboard":"/sota/video-super-resolution-on-msu-super-1","task":"Video Super-Resolution","dataset":"MSU Super-Resolution for Video Compression","model":"RSDN + x265","rank_in_archive_order":68,"of":85,"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},{"leaderboard":"/sota/video-super-resolution-on-msu-super-1","task":"Video Super-Resolution","dataset":"MSU Super-Resolution for Video Compression","model":"RSDN + vvenc","rank_in_archive_order":73,"of":85,"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},{"leaderboard":"/sota/video-super-resolution-on-msu-super-1","task":"Video Super-Resolution","dataset":"MSU Super-Resolution for Video Compression","model":"RSDN + uavs3e","rank_in_archive_order":78,"of":85,"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},{"leaderboard":"/sota/video-super-resolution-on-msu-super-1","task":"Video Super-Resolution","dataset":"MSU Super-Resolution for Video Compression","model":"RSDN + aomenc","rank_in_archive_order":79,"of":85,"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},{"leaderboard":"/sota/video-super-resolution-on-msu-vsr-benchmark","task":"Video Super-Resolution","dataset":"MSU Video Super Resolution Benchmark: Detail Restoration","model":"RSDN","rank_in_archive_order":10,"of":32,"metrics":{"1 - LPIPS":"0.819","ERQAv1.0":"0.667","FPS":"1.961","PSNR":"25.321","QRCRv1.0":"0.619","SSIM":"0.826","Subjective score":"5.566"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-vid4-4x-upscaling-1","task":"Video Super-Resolution","dataset":"Vid4 - 4x upscaling - BD degradation","model":"RSDN","rank_in_archive_order":9,"of":18,"metrics":{"PSNR":"27.92","SSIM":"0.8505"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.00455","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}