{"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/new-techniques-for-preserving-global","title":"New Techniques for Preserving Global Structure and Denoising with Low Information Loss in Single-Image Super-Resolution","arxiv_id":"1805.03383","date":"2018-05-09","proceeding":null,"authors":["Yijie Bei","Alex Damian","Shijia Hu","Sachit Menon","Nikhil Ravi","Cynthia Rudin"],"abstract":"This work identifies and addresses two important technical challenges in\nsingle-image super-resolution: (1) how to upsample an image without magnifying\nnoise and (2) how to preserve large scale structure when upsampling. We\nsummarize the techniques we developed for our second place entry in Track 1\n(Bicubic Downsampling), seventh place entry in Track 2 (Realistic Adverse\nConditions), and seventh place entry in Track 3 (Realistic difficult) in the\n2018 NTIRE Super-Resolution Challenge. Furthermore, we present new neural\nnetwork architectures that specifically address the two challenges listed\nabove: denoising and preservation of large-scale structure.","url_abs":"http://arxiv.org/abs/1805.03383v2","url_pdf":"http://arxiv.org/pdf/1805.03383v2.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":"new-techniques-for-preserving-global","repo_url":"https://github.com/nikhilvravi/DukeSR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}