{"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-proximal-operators-using-denoising","title":"Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems","arxiv_id":"1704.03488","date":"2017-04-11","proceeding":"ICCV 2017 10","authors":["Tim Meinhardt","Michael Moeller","Caner Hazirbas","Daniel Cremers"],"abstract":"While variational methods have been among the most powerful tools for solving\nlinear inverse problems in imaging, deep (convolutional) neural networks have\nrecently taken the lead in many challenging benchmarks. A remaining drawback of\ndeep learning approaches is their requirement for an expensive retraining\nwhenever the specific problem, the noise level, noise type, or desired measure\nof fidelity changes. On the contrary, variational methods have a plug-and-play\nnature as they usually consist of separate data fidelity and regularization\nterms.\n  In this paper we study the possibility of replacing the proximal operator of\nthe regularization used in many convex energy minimization algorithms by a\ndenoising neural network. The latter therefore serves as an implicit natural\nimage prior, while the data term can still be chosen independently. Using a\nfixed denoising neural network in exemplary problems of image deconvolution\nwith different blur kernels and image demosaicking, we obtain state-of-the-art\nreconstruction results. These indicate the high generalizability of our\napproach and a reduction of the need for problem-specific training.\nAdditionally, we discuss novel results on the analysis of possible optimization\nalgorithms to incorporate the network into, as well as the choices of algorithm\nparameters and their relation to the noise level the neural network is trained\non.","url_abs":"http://arxiv.org/abs/1704.03488v2","url_pdf":"http://arxiv.org/pdf/1704.03488v2.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-proximal-operators-using-denoising","repo_url":"https://github.com/tum-vision/learn_prox_ops","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"demosaicking","task_name":"Demosaicking"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-deconvolution","task_name":"Image Deconvolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.03488","atlas_url":"https://app.syntology.ai/?focus=1704.03488","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.03488"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/tum-vision/learn_prox_ops","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"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":1,"samples":[{"code_sha256_prefix":"76e8ea4b4aad27b6","entry":"channelwise_metric","repo":"tum-vision/learn_prox_ops","repo_kind":"official","path":"src/experiment_demosaicking.py","file_url":"https://github.com/tum-vision/learn_prox_ops/blob/HEAD/src/experiment_demosaicking.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"76e8ea4b4aad27b6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}