{"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/difficulty-aware-image-super-resolution-via","title":"Difficulty-aware Image Super Resolution via Deep Adaptive Dual-Network","arxiv_id":"1904.05802","date":"2019-04-11","proceeding":null,"authors":["Jinghui Qin","Ziwei Xie","Yukai Shi","Wushao Wen"],"abstract":"Recently, deep learning based single image super-resolution(SR) approaches\nhave achieved great development. The state-of-the-art SR methods usually adopt\na feed-forward pipeline to establish a non-linear mapping between low-res(LR)\nand high-res(HR) images. However, due to treating all image regions equally\nwithout considering the difficulty diversity, these approaches meet an upper\nbound for optimization. To address this issue, we propose a novel SR approach\nthat discriminately processes each image region within an image by its\ndifficulty. Specifically, we propose a dual-way SR network that one way is\ntrained to focus on easy image regions and another is trained to handle hard\nimage regions. To identify whether a region is easy or hard, we propose a novel\nimage difficulty recognition network based on PSNR prior. Our SR approach that\nuses the region mask to adaptively enforce the dual-way SR network yields\nsuperior results. Extensive experiments on several standard benchmarks (e.g.,\nSet5, Set14, BSD100, and Urban100) show that our approach achieves\nstate-of-the-art performance.","url_abs":"http://arxiv.org/abs/1904.05802v2","url_pdf":"http://arxiv.org/pdf/1904.05802v2.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":"difficulty-aware-image-super-resolution-via","repo_url":"https://github.com/xzwlx/Difficulty-SR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"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}