{"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/detail-revealing-deep-video-super-resolution","title":"Detail-revealing Deep Video Super-resolution","arxiv_id":"1704.02738","date":"2017-04-10","proceeding":"ICCV 2017 10","authors":["Xin Tao","Hongyun Gao","Renjie Liao","Jue Wang","Jiaya Jia"],"abstract":"Previous CNN-based video super-resolution approaches need to align multiple\nframes to the reference. In this paper, we show that proper frame alignment and\nmotion compensation is crucial for achieving high quality results. We\naccordingly propose a `sub-pixel motion compensation' (SPMC) layer in a CNN\nframework. Analysis and experiments show the suitability of this layer in video\nSR. The final end-to-end, scalable CNN framework effectively incorporates the\nSPMC layer and fuses multiple frames to reveal image details. Our\nimplementation can generate visually and quantitatively high-quality results,\nsuperior to current state-of-the-arts, without the need of parameter tuning.","url_abs":"http://arxiv.org/abs/1704.02738v1","url_pdf":"http://arxiv.org/pdf/1704.02738v1.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":"detail-revealing-deep-video-super-resolution","repo_url":"https://github.com/jiangsutx/SPMC_VideoSR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"motion-compensation","task_name":"Motion Compensation"},{"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/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"SPMC","rank_in_archive_order":92,"of":104,"metrics":{"PSNR":"27.57","SSIM":"0.76"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-msu-video-upscalers","task":"Video Super-Resolution","dataset":"MSU Video Upscalers: Quality Enhancement","model":"SPMC","rank_in_archive_order":40,"of":48,"metrics":{"PSNR":"26.99","SSIM":"0.933","VMAF":"51.96"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-vid4-4x-upscaling","task":"Video Super-Resolution","dataset":"Vid4 - 4x upscaling","model":"DRDVSR","rank_in_archive_order":16,"of":27,"metrics":{"PSNR":"25.88","SSIM":"0.774"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.02738","atlas_url":"https://app.syntology.ai/?focus=1704.02738","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}