{"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/understanding-kernel-size-in-blind","title":"Understanding Kernel Size in Blind Deconvolution","arxiv_id":"1706.01797","date":"2017-06-06","proceeding":null,"authors":["Li Si-Yao","Dongwei Ren","Qian Yin"],"abstract":"Most blind deconvolution methods usually pre-define a large kernel size to\nguarantee the support domain. Blur kernel estimation error is likely to be\nintroduced, yielding severe artifacts in deblurring results. In this paper, we\nfirst theoretically and experimentally analyze the mechanism to estimation\nerror in oversized kernel, and show that it holds even on blurry images without\nnoises. Then to suppress this adverse effect, we propose a low rank-based\nregularization on blur kernel to exploit the structural information in degraded\nkernels, by which larger-kernel effect can be effectively suppressed. And we\npropose an efficient optimization algorithm to solve it. Experimental results\non benchmark datasets show that the proposed method is comparable with the\nstate-of-the-arts by accordingly setting proper kernel size, and performs much\nbetter in handling larger-size kernels quantitatively and qualitatively. The\ndeblurring results on real-world blurry images further validate the\neffectiveness of the proposed method.","url_abs":"http://arxiv.org/abs/1706.01797v5","url_pdf":"http://arxiv.org/pdf/1706.01797v5.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":"understanding-kernel-size-in-blind","repo_url":"https://github.com/lisiyaoATbnu/low_rank_kernel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"}],"methods":[{"method_slug":"large-kernel-size","method_name":"Large Kernel Size"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}