{"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/deep-mean-shift-priors-for-image-restoration","title":"Deep Mean-Shift Priors for Image Restoration","arxiv_id":"1709.03749","date":"2017-09-12","proceeding":"NeurIPS 2017 12","authors":["Siavash Arjomand Bigdeli","Meiguang Jin","Paolo Favaro","Matthias Zwicker"],"abstract":"In this paper we introduce a natural image prior that directly represents a\nGaussian-smoothed version of the natural image distribution. We include our\nprior in a formulation of image restoration as a Bayes estimator that also\nallows us to solve noise-blind image restoration problems. We show that the\ngradient of our prior corresponds to the mean-shift vector on the natural image\ndistribution. In addition, we learn the mean-shift vector field using denoising\nautoencoders, and use it in a gradient descent approach to perform Bayes risk\nminimization. We demonstrate competitive results for noise-blind deblurring,\nsuper-resolution, and demosaicing.","url_abs":"http://arxiv.org/abs/1709.03749v2","url_pdf":"http://arxiv.org/pdf/1709.03749v2.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":"deep-mean-shift-priors-for-image-restoration","repo_url":"https://github.com/siavashbigdeli/DMSP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"demosaicking","task_name":"Demosaicking"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"Deep Mean-Shift Priors","rank_in_archive_order":98,"of":104,"metrics":{"PSNR":"26.22"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.03749","atlas_url":"https://app.syntology.ai/?focus=1709.03749","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}