{"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/mssnet-multi-scale-stage-network-for-single","title":"MSSNet: Multi-Scale-Stage Network for Single Image Deblurring","arxiv_id":"2202.09652","date":"2022-02-19","proceeding":null,"authors":["Kiyeon Kim","Seungyong Lee","Sunghyun Cho"],"abstract":"Most of traditional single image deblurring methods before deep learning adopt a coarse-to-fine scheme that estimates a sharp image at a coarse scale and progressively refines it at finer scales. While this scheme has also been adopted to several deep learning-based approaches, recently a number of single-scale approaches have been introduced showing superior performance to previous coarse-to-fine approaches both in quality and computation time. In this paper, we revisit the coarse-to-fine scheme, and analyze defects of previous coarse-to-fine approaches that degrade their performance. Based on the analysis, we propose Multi-Scale-Stage Network (MSSNet), a novel deep learning-based approach to single image deblurring that adopts our remedies to the defects. Specifically, MSSNet adopts three novel technical components: stage configuration reflecting blur scales, an inter-scale information propagation scheme, and a pixel-shuffle-based multi-scale scheme. Our experiments show that MSSNet achieves the state-of-the-art performance in terms of quality, network size, and computation time.","url_abs":"https://arxiv.org/abs/2202.09652v3","url_pdf":"https://arxiv.org/pdf/2202.09652v3.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":"mssnet-multi-scale-stage-network-for-single","repo_url":"https://github.com/kky7/MSSNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"single-image-deblurring","task_name":"Single Image Deblurring"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"MSSNet-large","rank_in_archive_order":20,"of":56,"metrics":{"PSNR":"33.39","SSIM":"0.964"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"MSSNet","rank_in_archive_order":27,"of":56,"metrics":{"PSNR":"33.01","SSIM":"0.961"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"MSSNet-small","rank_in_archive_order":39,"of":56,"metrics":{"PSNR":"32.02","SSIM":"0.953"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-j-1","task":"Deblurring","dataset":"RealBlur-J","model":"MSSNet","rank_in_archive_order":12,"of":17,"metrics":{"PSNR (sRGB)":"32.1","Params(M)":"15.6","SSIM (sRGB)":"0.928"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-j-trained-on-gopro","task":"Deblurring","dataset":"RealBlur-J (trained on GoPro)","model":"MSSNet","rank_in_archive_order":9,"of":15,"metrics":{"PSNR (sRGB)":"28.79","SSIM (sRGB)":"0.879"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-r","task":"Deblurring","dataset":"RealBlur-R","model":"MSSNet","rank_in_archive_order":11,"of":17,"metrics":{"PSNR (sRGB)":"39.76","Params":"15.59","SSIM (sRGB)":"0.972"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-r-trained-on-gopro","task":"Deblurring","dataset":"RealBlur-R (trained on GoPro)","model":"MSSNet","rank_in_archive_order":9,"of":19,"metrics":{"PSNR (sRGB)":"35.93","SSIM (sRGB)":"0.953"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.09652","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}