{"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/deep-plug-and-play-super-resolution-for","title":"Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels","arxiv_id":"1903.12529","date":"2019-03-29","proceeding":"CVPR 2019 6","authors":["Kai Zhang","WangMeng Zuo","Lei Zhang"],"abstract":"While deep neural networks (DNN) based single image super-resolution (SISR)\nmethods are rapidly gaining popularity, they are mainly designed for the\nwidely-used bicubic degradation, and there still remains the fundamental\nchallenge for them to super-resolve low-resolution (LR) image with arbitrary\nblur kernels. In the meanwhile, plug-and-play image restoration has been\nrecognized with high flexibility due to its modular structure for easy plug-in\nof denoiser priors. In this paper, we propose a principled formulation and\nframework by extending bicubic degradation based deep SISR with the help of\nplug-and-play framework to handle LR images with arbitrary blur kernels.\nSpecifically, we design a new SISR degradation model so as to take advantage of\nexisting blind deblurring methods for blur kernel estimation. To optimize the\nnew degradation induced energy function, we then derive a plug-and-play\nalgorithm via variable splitting technique, which allows us to plug any\nsuper-resolver prior rather than the denoiser prior as a modular part.\nQuantitative and qualitative evaluations on synthetic and real LR images\ndemonstrate that the proposed deep plug-and-play super-resolution framework is\nflexible and effective to deal with blurry LR images.","url_abs":"http://arxiv.org/abs/1903.12529v1","url_pdf":"http://arxiv.org/pdf/1903.12529v1.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":"deep-plug-and-play-super-resolution-for","repo_url":"https://github.com/cszn/DPSR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.12529","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}