{"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/super-resolution-using-convolutional-neural","title":"Super-Resolution using Convolutional Neural Networks without Any Checkerboard Artifacts","arxiv_id":"1806.02658","date":"2018-06-07","proceeding":null,"authors":["Yusuke Sugawara","Sayaka Shiota","Hitoshi Kiya"],"abstract":"It is well-known that a number of excellent super-resolution (SR) methods\nusing convolutional neural networks (CNNs) generate checkerboard artifacts. A\ncondition to avoid the checkerboard artifacts is proposed in this paper. So\nfar, checkerboard artifacts have been mainly studied for linear multirate\nsystems, but the condition to avoid checkerboard artifacts can not be applied\nto CNNs due to the non-linearity of CNNs. We extend the avoiding condition for\nCNNs, and apply the proposed structure to some typical SR methods to confirm\nthe effectiveness of the new scheme. Experiment results demonstrate that the\nproposed structure can perfectly avoid to generate checkerboard artifacts under\ntwo loss conditions: mean square error and perceptual loss, while keeping\nexcellent properties that the SR methods have.","url_abs":"http://arxiv.org/abs/1806.02658v1","url_pdf":"http://arxiv.org/pdf/1806.02658v1.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":"super-resolution-using-convolutional-neural","repo_url":"https://github.com/r06922019/butt_lion_paper_notes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.02658","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}