{"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/multi-scale-deep-neural-networks-for-real","title":"Multi-scale deep neural networks for real image super-resolution","arxiv_id":"1904.10698","date":"2019-04-24","proceeding":null,"authors":["Shangqi Gao","Xiahai Zhuang"],"abstract":"Single image super-resolution (SR) is extremely difficult if the upscaling\nfactors of image pairs are unknown and different from each other, which is\ncommon in real image SR. To tackle the difficulty, we develop two multi-scale\ndeep neural networks (MsDNN) in this work. Firstly, due to the high computation\ncomplexity in high-resolution spaces, we process an input image mainly in two\ndifferent downscaling spaces, which could greatly lower the usage of GPU\nmemory. Then, to reconstruct the details of an image, we design a multi-scale\nresidual network (MsRN) in the downscaling spaces based on the residual blocks.\nBesides, we propose a multi-scale dense network based on the dense blocks to\ncompare with MsRN. Finally, our empirical experiments show the robustness of\nMsDNN for image SR when the upscaling factor is unknown. According to the\npreliminary results of NTIRE 2019 image SR challenge, our team\n(ZXHresearch@fudan) ranks 21-st among all participants. The implementation of\nMsDNN is released https://github.com/shangqigao/gsq-image-SR","url_abs":"http://arxiv.org/abs/1904.10698v1","url_pdf":"http://arxiv.org/pdf/1904.10698v1.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":"multi-scale-deep-neural-networks-for-real","repo_url":"https://github.com/shangqigao/gsq-image-SR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"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=1904.10698","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}