{"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-improving-video-super-resolution","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","arxiv_id":"2104.13371","date":"2021-04-27","proceeding":"CVPR 2022 1","authors":["Kelvin C. K. Chan","Shangchen Zhou","Xiangyu Xu","Chen Change Loy"],"abstract":"A recurrent structure is a popular framework choice for the task of video super-resolution. The state-of-the-art method BasicVSR adopts bidirectional propagation with feature alignment to effectively exploit information from the entire input video. In this study, we redesign BasicVSR by proposing second-order grid propagation and flow-guided deformable alignment. We show that by empowering the recurrent framework with the enhanced propagation and alignment, one can exploit spatiotemporal information across misaligned video frames more effectively. The new components lead to an improved performance under a similar computational constraint. In particular, our model BasicVSR++ surpasses BasicVSR by 0.82 dB in PSNR with similar number of parameters. In addition to video super-resolution, BasicVSR++ generalizes well to other video restoration tasks such as compressed video enhancement. In NTIRE 2021, BasicVSR++ obtains three champions and one runner-up in the Video Super-Resolution and Compressed Video Enhancement Challenges. Codes and models will be released to MMEditing.","url_abs":"https://arxiv.org/abs/2104.13371v1","url_pdf":"https://arxiv.org/pdf/2104.13371v1.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-improving-video-super-resolution","repo_url":"https://github.com/open-mmlab/mmediting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"basicvsr-improving-video-super-resolution","repo_url":"https://github.com/ckkelvinchan/basicvsr_plusplus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"basicvsr-improving-video-super-resolution","repo_url":"https://github.com/renyang-home/ntire22_venh_sr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"analog-video-restoration","task_name":"Analog Video Restoration"},{"task_slug":"snow-removal","task_name":"Snow Removal"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"video-enhancement","task_name":"Video Enhancement"},{"task_slug":"video-restoration","task_name":"Video Restoration"},{"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/analog-video-restoration-on-tape","task":"Analog Video Restoration","dataset":"TAPE","model":"BasicVSR++","rank_in_archive_order":5,"of":7,"metrics":{"LPIPS":"0.098","PSNR":"31.66","SSIM":"0.916","VMAF":"78.91"},"uses_additional_data":false},{"leaderboard":"/sota/video-enhancement-on-mfqe-v2","task":"Video Enhancement","dataset":"MFQE v2","model":"BasicVSR++","rank_in_archive_order":1,"of":6,"metrics":{"Incremental PSNR":"1.10"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-msu-video-upscalers","task":"Video Super-Resolution","dataset":"MSU Video Upscalers: Quality Enhancement","model":"BasicVsr++RD","rank_in_archive_order":28,"of":48,"metrics":{"LPIPS":"0.334","PSNR":"30.98","SSIM":"0.881"},"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":3,"of":7,"metrics":{"PSNR":"40.72","SSIM":"0.9722"},"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":10,"of":27,"metrics":{"PSNR":"27.79","SSIM":"0.8400"},"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":3,"of":18,"metrics":{"PSNR":"29.04","SSIM":"0.8753"},"uses_additional_data":false},{"leaderboard":"/sota/video-deraining-on-vrds","task":"Video deraining","dataset":"VRDS","model":"BasicVSR++","rank_in_archive_order":5,"of":8,"metrics":{"PSNR":"29.75","SSIM":"0.9171"},"uses_additional_data":false},{"leaderboard":"/sota/video-deraining-on-video-waterdrop-removal","task":"Video deraining","dataset":"Video Waterdrop Removal Dataset","model":"BasicVSR++","rank_in_archive_order":2,"of":5,"metrics":{"PSNR":"32.37","SSIM":"0.9792"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.13371","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}