{"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/basicvsr-the-search-for-essential-components","title":"BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond","arxiv_id":"2012.02181","date":"2020-12-03","proceeding":"CVPR 2021 1","authors":["Kelvin C. K. Chan","Xintao Wang","Ke Yu","Chao Dong","Chen Change Loy"],"abstract":"Video super-resolution (VSR) approaches tend to have more components than the image counterparts as they need to exploit the additional temporal dimension. Complex designs are not uncommon. In this study, we wish to untangle the knots and reconsider some most essential components for VSR guided by four basic functionalities, i.e., Propagation, Alignment, Aggregation, and Upsampling. By reusing some existing components added with minimal redesigns, we show a succinct pipeline, BasicVSR, that achieves appealing improvements in terms of speed and restoration quality in comparison to many state-of-the-art algorithms. We conduct systematic analysis to explain how such gain can be obtained and discuss the pitfalls. We further show the extensibility of BasicVSR by presenting an information-refill mechanism and a coupled propagation scheme to facilitate information aggregation. The BasicVSR and its extension, IconVSR, can serve as strong baselines for future VSR approaches.","url_abs":"https://arxiv.org/abs/2012.02181v2","url_pdf":"https://arxiv.org/pdf/2012.02181v2.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":"basicvsr-the-search-for-essential-components","repo_url":"https://github.com/Feynman1999/MgeEditing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"basicvsr-the-search-for-essential-components","repo_url":"https://github.com/Feynman1999/basicVSR_mge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"basicvsr-the-search-for-essential-components","repo_url":"https://github.com/XPixelGroup/BasicSR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"basicvsr-the-search-for-essential-components","repo_url":"https://github.com/xinntao/BasicSR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"basicvsr-the-search-for-essential-components","repo_url":"https://github.com/code-implementation1/Code9/tree/main/EDSR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"basicvsr-the-search-for-essential-components","repo_url":"https://github.com/open-mmlab/mmediting/blob/master/configs/restorers/basicvsr/README.md","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"video-super-resolution","task_name":"Video Super-Resolution"},{"task_slug":"video-deraining","task_name":"Video deraining"}],"methods":[{"method_slug":"basicvsr","method_name":"BasicVSR"},{"method_slug":"pixelshuffle","method_name":"PixelShuffle"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"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":"BasicVSR + x264","rank_in_archive_order":24,"of":85,"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},{"leaderboard":"/sota/video-super-resolution-on-msu-super-1","task":"Video Super-Resolution","dataset":"MSU Super-Resolution for Video Compression","model":"BasicVSR + x265","rank_in_archive_order":30,"of":85,"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},{"leaderboard":"/sota/video-super-resolution-on-msu-super-1","task":"Video Super-Resolution","dataset":"MSU Super-Resolution for Video Compression","model":"BasicVSR + vvenc","rank_in_archive_order":35,"of":85,"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},{"leaderboard":"/sota/video-super-resolution-on-msu-super-1","task":"Video Super-Resolution","dataset":"MSU Super-Resolution for Video Compression","model":"BasicVSR + aomenc","rank_in_archive_order":36,"of":85,"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},{"leaderboard":"/sota/video-super-resolution-on-msu-super-1","task":"Video Super-Resolution","dataset":"MSU Super-Resolution for Video Compression","model":"BasicVSR + uavs3e","rank_in_archive_order":39,"of":85,"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},{"leaderboard":"/sota/video-super-resolution-on-msu-vsr-benchmark","task":"Video Super-Resolution","dataset":"MSU Video Super Resolution Benchmark: Detail Restoration","model":"BasicVSR","rank_in_archive_order":2,"of":32,"metrics":{"1 - LPIPS":"0.934","ERQAv1.0":"0.75","FPS":"2.128","PSNR":"31.443","QRCRv1.0":"0.709","SSIM":"0.9","Subjective score":"7.186"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-udm10-4x-upscaling","task":"Video Super-Resolution","dataset":"UDM10 - 4x upscaling","model":"IconVSR","rank_in_archive_order":5,"of":7,"metrics":{"PSNR":"40.03","SSIM":"0.9694"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-udm10-4x-upscaling","task":"Video Super-Resolution","dataset":"UDM10 - 4x upscaling","model":"BasicVSR","rank_in_archive_order":6,"of":7,"metrics":{"PSNR":"39.96","SSIM":"0.9694"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-vid4-4x-upscaling","task":"Video Super-Resolution","dataset":"Vid4 - 4x upscaling","model":"IconVSR","rank_in_archive_order":12,"of":27,"metrics":{"PSNR":"27.39","SSIM":"0.8279"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-vid4-4x-upscaling","task":"Video Super-Resolution","dataset":"Vid4 - 4x upscaling","model":"BasicVSR","rank_in_archive_order":14,"of":27,"metrics":{"PSNR":"27.24","SSIM":"0.8251"},"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":"IconVSR","rank_in_archive_order":7,"of":18,"metrics":{"PSNR":"28.04","SSIM":"0.8570"},"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":"BasicVSR","rank_in_archive_order":8,"of":18,"metrics":{"PSNR":"27.96","SSIM":"0.8553"},"uses_additional_data":false},{"leaderboard":"/sota/video-deraining-on-vrds","task":"Video deraining","dataset":"VRDS","model":"BasicVSR","rank_in_archive_order":7,"of":8,"metrics":{"PSNR":"28.35","SSIM":"0.8990"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.02181","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}