{"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/sesr-single-image-super-resolution-with","title":"SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks","arxiv_id":"1801.10319","date":"2018-01-31","proceeding":null,"authors":["Xi Cheng","Xiang Li","Ying Tai","Jian Yang"],"abstract":"Single image super resolution is a very important computer vision task, with\na wide range of applications. In recent years, the depth of the\nsuper-resolution model has been constantly increasing, but with a small\nincrease in performance, it has brought a huge amount of computation and memory\nconsumption. In this work, in order to make the super resolution models more\neffective, we proposed a novel single image super resolution method via\nrecursive squeeze and excitation networks (SESR). By introducing the squeeze\nand excitation module, our SESR can model the interdependencies and\nrelationships between channels and that makes our model more efficiency. In\naddition, the recursive structure and progressive reconstruction method in our\nmodel minimized the layers and parameters and enabled SESR to simultaneously\ntrain multi-scale super resolution in a single model. After evaluating on four\nbenchmark test sets, our model is proved to be above the state-of-the-art\nmethods in terms of speed and accuracy.","url_abs":"http://arxiv.org/abs/1801.10319v1","url_pdf":"http://arxiv.org/pdf/1801.10319v1.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":"sesr-single-image-super-resolution-with","repo_url":"https://github.com/opteroncx/SESR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"SESR","rank_in_archive_order":40,"of":71,"metrics":{"PSNR":"27.42","SSIM":"0.737"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"SESR","rank_in_archive_order":72,"of":104,"metrics":{"PSNR":"28.32","SSIM":"0.784"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"SESR","rank_in_archive_order":53,"of":65,"metrics":{"PSNR":"25.42","SSIM":"0.771"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}