{"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/image-super-resolution-via-dual-state","title":"Image Super-Resolution via Dual-State Recurrent Networks","arxiv_id":"1805.02704","date":"2018-05-07","proceeding":"CVPR 2018 6","authors":["Wei Han","Shiyu Chang","Ding Liu","Mo Yu","Michael Witbrock","Thomas S. Huang"],"abstract":"Advances in image super-resolution (SR) have recently benefited significantly\nfrom rapid developments in deep neural networks. Inspired by these recent\ndiscoveries, we note that many state-of-the-art deep SR architectures can be\nreformulated as a single-state recurrent neural network (RNN) with finite\nunfoldings. In this paper, we explore new structures for SR based on this\ncompact RNN view, leading us to a dual-state design, the Dual-State Recurrent\nNetwork (DSRN). Compared to its single state counterparts that operate at a\nfixed spatial resolution, DSRN exploits both low-resolution (LR) and\nhigh-resolution (HR) signals jointly. Recurrent signals are exchanged between\nthese states in both directions (both LR to HR and HR to LR) via delayed\nfeedback. Extensive quantitative and qualitative evaluations on benchmark\ndatasets and on a recent challenge demonstrate that the proposed DSRN performs\nfavorably against state-of-the-art algorithms in terms of both memory\nconsumption and predictive accuracy.","url_abs":"http://arxiv.org/abs/1805.02704v1","url_pdf":"http://arxiv.org/pdf/1805.02704v1.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":"image-super-resolution-via-dual-state","repo_url":"https://github.com/WeiHan3/dsrn","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":"DSRN","rank_in_archive_order":48,"of":71,"metrics":{"PSNR":"27.25","SSIM":"0.724"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"DSRN","rank_in_archive_order":79,"of":104,"metrics":{"PSNR":"28.07","SSIM":"0.770"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"DSRN","rank_in_archive_order":57,"of":65,"metrics":{"PSNR":"25.08","SSIM":"0.747"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.02704","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}