{"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/learning-a-single-convolutional-super","title":"Learning a Single Convolutional Super-Resolution Network for Multiple Degradations","arxiv_id":"1712.06116","date":"2017-12-17","proceeding":"CVPR 2018 6","authors":["Kai Zhang","WangMeng Zuo","Lei Zhang"],"abstract":"Recent years have witnessed the unprecedented success of deep convolutional\nneural networks (CNNs) in single image super-resolution (SISR). However,\nexisting CNN-based SISR methods mostly assume that a low-resolution (LR) image\nis bicubicly downsampled from a high-resolution (HR) image, thus inevitably\ngiving rise to poor performance when the true degradation does not follow this\nassumption. Moreover, they lack scalability in learning a single model to\nnon-blindly deal with multiple degradations. To address these issues, we\npropose a general framework with dimensionality stretching strategy that\nenables a single convolutional super-resolution network to take two key factors\nof the SISR degradation process, i.e., blur kernel and noise level, as input.\nConsequently, the super-resolver can handle multiple and even spatially variant\ndegradations, which significantly improves the practicability. Extensive\nexperimental results on synthetic and real LR images show that the proposed\nconvolutional super-resolution network not only can produce favorable results\non multiple degradations but also is computationally efficient, providing a\nhighly effective and scalable solution to practical SISR applications.","url_abs":"http://arxiv.org/abs/1712.06116v2","url_pdf":"http://arxiv.org/pdf/1712.06116v2.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":"learning-a-single-convolutional-super","repo_url":"https://github.com/cszn/SRMD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"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-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"SRMDNF","rank_in_archive_order":37,"of":71,"metrics":{"PSNR":"27.49","SSIM":"0.734"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"SRMDNF","rank_in_archive_order":71,"of":104,"metrics":{"PSNR":"28.35","SSIM":"0.777"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"SRMDNF","rank_in_archive_order":48,"of":65,"metrics":{"PSNR":"25.68","SSIM":"0.773"},"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":"SRMD","rank_in_archive_order":27,"of":32,"metrics":{"1 - LPIPS":"0.877","ERQAv1.0":"0.594","FPS":"5.882","PSNR":"27.672","QRCRv1.0":"0","SSIM":"0.834","Subjective score":"3.468"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-msu-video-upscalers","task":"Video Super-Resolution","dataset":"MSU Video Upscalers: Quality Enhancement","model":"SRMD","rank_in_archive_order":31,"of":48,"metrics":{"LPIPS":"0.349","PSNR":"30.96","SSIM":"0.852"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.06116","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}