{"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/learning-blind-motion-deblurring","title":"Learning Blind Motion Deblurring","arxiv_id":"1708.04208","date":"2017-08-14","proceeding":"ICCV 2017 10","authors":["Patrick Wieschollek","Michael Hirsch","Bernhard Schölkopf","Hendrik P. A. Lensch"],"abstract":"As handheld video cameras are now commonplace and available in every\nsmartphone, images and videos can be recorded almost everywhere at anytime.\nHowever, taking a quick shot frequently yields a blurry result due to unwanted\ncamera shake during recording or moving objects in the scene. Removing these\nartifacts from the blurry recordings is a highly ill-posed problem as neither\nthe sharp image nor the motion blur kernel is known. Propagating information\nbetween multiple consecutive blurry observations can help restore the desired\nsharp image or video. Solutions for blind deconvolution based on neural\nnetworks rely on a massive amount of ground-truth data which is hard to\nacquire. In this work, we propose an efficient approach to produce a\nsignificant amount of realistic training data and introduce a novel recurrent\nnetwork architecture to deblur frames taking temporal information into account,\nwhich can efficiently handle arbitrary spatial and temporal input sizes. We\ndemonstrate the versatility of our approach in a comprehensive comparison on a\nnumber of challening real-world examples.","url_abs":"http://arxiv.org/abs/1708.04208v1","url_pdf":"http://arxiv.org/pdf/1708.04208v1.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":"learning-blind-motion-deblurring","repo_url":"https://github.com/cgtuebingen/learning-blind-motion-deblurring","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.04208","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}