{"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/a-simple-local-minimal-intensity-prior-and-an","title":"A Simple Local Minimal Intensity Prior and An Improved Algorithm for Blind Image Deblurring","arxiv_id":"1906.06642","date":"2020-10-29","proceeding":null,"authors":[],"abstract":"Blind image deblurring is a long standing challenging problem in image\nprocessing and low-level vision. Recently, sophisticated priors such as dark\nchannel prior, extreme channel prior, and local maximum gradient prior, have\nshown promising effectiveness. However, these methods are computationally\nexpensive. Meanwhile, since these priors involved subproblems cannot be solved\nexplicitly, approximate solution is commonly used, which limits the best\nexploitation of their capability. To address these problems, this work firstly\nproposes a simplified sparsity prior of local minimal pixels, namely patch-wise\nminimal pixels (PMP). The PMP of clear images is much more sparse than that of\nblurred ones, and hence is very effective in discriminating between clear and\nblurred images. Then, a novel algorithm is designed to efficiently exploit the\nsparsity of PMP in deblurring. The new algorithm flexibly imposes sparsity\ninducing on the PMP under the MAP framework rather than directly uses the half\nquadratic splitting algorithm. By this, it avoids non-rigorous approximation\nsolution in existing algorithms, while being much more computationally\nefficient. Extensive experiments demonstrate that the proposed algorithm can\nachieve better practical stability compared with state-of-the-arts. In terms of\ndeblurring quality, robustness and computational efficiency, the new algorithm\nis superior to state-of-the-arts. Code for reproducing the results of the new\nmethod is available at https://github.com/FWen/deblur-pmp.git.","url_abs":"http://arxiv.org/abs/1906.06642v5","url_pdf":"http://arxiv.org/pdf/1906.06642v5.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":"a-simple-local-minimal-intensity-prior-and-an","repo_url":"https://github.com/FWen/deblur-pmp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"blind-image-deblurring","task_name":"Blind Image Deblurring"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}