{"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-neural-approach-to-blind-motion-deblurring","title":"A Neural Approach to Blind Motion Deblurring","arxiv_id":"1603.04771","date":"2016-03-15","proceeding":null,"authors":["Ayan Chakrabarti"],"abstract":"We present a new method for blind motion deblurring that uses a neural\nnetwork trained to compute estimates of sharp image patches from observations\nthat are blurred by an unknown motion kernel. Instead of regressing directly to\npatch intensities, this network learns to predict the complex Fourier\ncoefficients of a deconvolution filter to be applied to the input patch for\nrestoration. For inference, we apply the network independently to all\noverlapping patches in the observed image, and average its outputs to form an\ninitial estimate of the sharp image. We then explicitly estimate a single\nglobal blur kernel by relating this estimate to the observed image, and finally\nperform non-blind deconvolution with this kernel. Our method exhibits accuracy\nand robustness close to state-of-the-art iterative methods, while being much\nfaster when parallelized on GPU hardware.","url_abs":"http://arxiv.org/abs/1603.04771v2","url_pdf":"http://arxiv.org/pdf/1603.04771v2.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-neural-approach-to-blind-motion-deblurring","repo_url":"https://github.com/ayanc/ndeblur","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-neural-approach-to-blind-motion-deblurring","repo_url":"https://github.com/donggong1/learn-optimizer-rgdn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1603.04771","atlas_url":"https://app.syntology.ai/?focus=1603.04771","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}