{"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/blind-image-deconvolution-using-deep","title":"Blind Image Deconvolution using Deep Generative Priors","arxiv_id":"1802.04073","date":"2018-02-12","proceeding":null,"authors":["Muhammad Asim","Fahad Shamshad","Ali Ahmed"],"abstract":"This paper proposes a novel approach to regularize the \\textit{ill-posed} and\n\\textit{non-linear} blind image deconvolution (blind deblurring) using deep\ngenerative networks as priors. We employ two separate generative models --- one\ntrained to produce sharp images while the other trained to generate blur\nkernels from lower-dimensional parameters. To deblur, we propose an alternating\ngradient descent scheme operating in the latent lower-dimensional space of each\nof the pretrained generative models. Our experiments show promising deblurring\nresults on images even under large blurs, and heavy noise. To address the\nshortcomings of generative models such as mode collapse, we augment our\ngenerative priors with classical image priors and report improved performance\non complex image datasets. The deblurring performance depends on how well the\nrange of the generator spans the image class. Interestingly, our experiments\nshow that even an untrained structured (convolutional) generative networks acts\nas an image prior in the image deblurring context allowing us to extend our\nresults to more diverse natural image datasets.","url_abs":"http://arxiv.org/abs/1802.04073v4","url_pdf":"http://arxiv.org/pdf/1802.04073v4.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":"blind-image-deconvolution-using-deep","repo_url":"https://github.com/axium/Blind-Image-Deconvolution-using-Deep-Generative-Priors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"image-deconvolution","task_name":"Image Deconvolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.04073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04073"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/axium/Blind-Image-Deconvolution-using-Deep-Generative-Priors","reach":null}],"summary":{"ran_violates":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"64c8bd943cd51891","entry":"step_size","repo":"axium/Blind-Image-Deconvolution-using-Deep-Generative-Priors","repo_kind":"listed","path":"deblurring_celeba_algorithm_1.py","file_url":"https://github.com/axium/Blind-Image-Deconvolution-using-Deep-Generative-Priors/blob/HEAD/deblurring_celeba_algorithm_1.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64c8bd943cd51891"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}