{"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/adversarial-regularizers-in-inverse-problems","title":"Adversarial Regularizers in Inverse Problems","arxiv_id":"1805.11572","date":"2018-05-29","proceeding":"NeurIPS 2018 12","authors":["Sebastian Lunz","Ozan Öktem","Carola-Bibiane Schönlieb"],"abstract":"Inverse Problems in medical imaging and computer vision are traditionally\nsolved using purely model-based methods. Among those variational regularization\nmodels are one of the most popular approaches. We propose a new framework for\napplying data-driven approaches to inverse problems, using a neural network as\na regularization functional. The network learns to discriminate between the\ndistribution of ground truth images and the distribution of unregularized\nreconstructions. Once trained, the network is applied to the inverse problem by\nsolving the corresponding variational problem. Unlike other data-based\napproaches for inverse problems, the algorithm can be applied even if only\nunsupervised training data is available. Experiments demonstrate the potential\nof the framework for denoising on the BSDS dataset and for computed tomography\nreconstruction on the LIDC dataset.","url_abs":"http://arxiv.org/abs/1805.11572v2","url_pdf":"http://arxiv.org/pdf/1805.11572v2.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":"adversarial-regularizers-in-inverse-problems","repo_url":"https://github.com/lunz-s/DeepAdverserialRegulariser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"adversarial-regularizers-in-inverse-problems","repo_url":"https://github.com/Zakobian/CT_framework_","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.11572","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}