{"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/robust-blind-deconvolution-via-mirror-descent","title":"Robust Blind Deconvolution via Mirror Descent","arxiv_id":"1803.08137","date":"2018-03-21","proceeding":null,"authors":["Sathya N. Ravi","Ronak Mehta","Vikas Singh"],"abstract":"We revisit the Blind Deconvolution problem with a focus on understanding its\nrobustness and convergence properties. Provable robustness to noise and other\nperturbations is receiving recent interest in vision, from obtaining immunity\nto adversarial attacks to assessing and describing failure modes of algorithms\nin mission critical applications. Further, many blind deconvolution methods\nbased on deep architectures internally make use of or optimize the basic\nformulation, so a clearer understanding of how this sub-module behaves, when it\ncan be solved, and what noise injection it can tolerate is a first order\nrequirement. We derive new insights into the theoretical underpinnings of blind\ndeconvolution. The algorithm that emerges has nice convergence guarantees and\nis provably robust in a sense we formalize in the paper. Interestingly, these\ntechnical results play out very well in practice, where on standard datasets\nour algorithm yields results competitive with or superior to the state of the\nart. Keywords: blind deconvolution, robust continuous optimization","url_abs":"http://arxiv.org/abs/1803.08137v1","url_pdf":"http://arxiv.org/pdf/1803.08137v1.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":"robust-blind-deconvolution-via-mirror-descent","repo_url":"https://github.com/sravi-uwmadison/prida","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"robust-blind-deconvolution-via-mirror-descent","repo_url":"https://github.com/tianyishan/Blind_Deconvolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"robust-blind-deconvolution-via-mirror-descent","repo_url":"https://github.com/tianyishan/PRIDA_CPP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"robust-blind-deconvolution-via-mirror-descent","repo_url":"https://github.com/vsingh-group/prida","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"affine-coupling","method_name":"Affine Coupling"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.08137","atlas_url":"https://app.syntology.ai/?focus=1803.08137","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}