{"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/advanced-super-resolution-using-lossless","title":"Advanced Super-Resolution using Lossless Pooling Convolutional Networks","arxiv_id":"1812.06023","date":"2018-12-14","proceeding":null,"authors":["Farzad Toutounchi","Ebroul Izquierdo"],"abstract":"In this paper, we present a novel deep learning-based approach for still\nimage super-resolution, that unlike the mainstream models does not rely solely\non the input low resolution image for high quality upsampling, and takes\nadvantage of a set of artificially created auxiliary self-replicas of the input\nimage that are incorporated in the neural network to create an enhanced and\naccurate upscaling scheme. Inclusion of the proposed lossless pooling layers,\nand the fusion of the input self-replicas enable the model to exploit the high\ncorrelation between multiple instances of the same content, and eventually\nresult in significant improvements in the quality of the super-resolution,\nwhich is confirmed by extensive evaluations.","url_abs":"http://arxiv.org/abs/1812.06023v1","url_pdf":"http://arxiv.org/pdf/1812.06023v1.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":"advanced-super-resolution-using-lossless","repo_url":"https://github.com/gan3sh500/custom-pooling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"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}