{"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/lightweight-and-efficient-image-super","title":"Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network","arxiv_id":"1811.12546","date":"2018-11-30","proceeding":null,"authors":["Jun-Ho Choi","Jun-Hyuk Kim","Manri Cheon","Jong-Seok Lee"],"abstract":"Recently, several deep learning-based image super-resolution methods have\nbeen developed by stacking massive numbers of layers. However, this leads too\nlarge model sizes and high computational complexities, thus some recursive\nparameter-sharing methods have been also proposed. Nevertheless, their designs\ndo not properly utilize the potential of the recursive operation. In this\npaper, we propose a novel, lightweight, and efficient super-resolution method\nto maximize the usefulness of the recursive architecture, by introducing block\nstate-based recursive network. By taking advantage of utilizing the block\nstate, the recursive part of our model can easily track the status of the\ncurrent image features. We show the benefits of the proposed method in terms of\nmodel size, speed, and efficiency. In addition, we show that our method\noutperforms the other state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1811.12546v1","url_pdf":"http://arxiv.org/pdf/1811.12546v1.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":"lightweight-and-efficient-image-super","repo_url":"https://github.com/idearibosome/tf-bsrn-sr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"lightweight-and-efficient-image-super","repo_url":"https://github.com/manricheon/manricheon.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"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":[{"leaderboard":"/sota/image-super-resolution-on-bsd100-4x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 4x upscaling","model":"BSRN","rank_in_archive_order":33,"of":71,"metrics":{"PSNR":"27.57","SSIM":"0.7353"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"BSRN","rank_in_archive_order":59,"of":104,"metrics":{"PSNR":"28.56","SSIM":"0.7803"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"BSRN","rank_in_archive_order":46,"of":65,"metrics":{"PSNR":"26.03","SSIM":"0.7835"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}