{"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/learned-primal-dual-reconstruction","title":"Learned Primal-dual Reconstruction","arxiv_id":"1707.06474","date":"2017-07-20","proceeding":null,"authors":["Jonas Adler","Ozan Öktem"],"abstract":"We propose the Learned Primal-Dual algorithm for tomographic reconstruction.\nThe algorithm accounts for a (possibly non-linear) forward operator in a deep\nneural network by unrolling a proximal primal-dual optimization method, but\nwhere the proximal operators have been replaced with convolutional neural\nnetworks. The algorithm is trained end-to-end, working directly from raw\nmeasured data and it does not depend on any initial reconstruction such as FBP.\n  We compare performance of the proposed method on low dose CT reconstruction\nagainst FBP, TV, and deep learning based post-processing of FBP. For the\nShepp-Logan phantom we obtain >6dB PSNR improvement against all compared\nmethods. For human phantoms the corresponding improvement is 6.6dB over TV and\n2.2dB over learned post-processing along with a substantial improvement in the\nSSIM. Finally, our algorithm involves only ten forward-back-projection\ncomputations, making the method feasible for time critical clinical\napplications.","url_abs":"http://arxiv.org/abs/1707.06474v3","url_pdf":"http://arxiv.org/pdf/1707.06474v3.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":"learned-primal-dual-reconstruction","repo_url":"https://github.com/odlgroup/odl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MPL-2.0"}},{"paper_slug":"learned-primal-dual-reconstruction","repo_url":"https://github.com/Zakobian/CT_framework_","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learned-primal-dual-reconstruction","repo_url":"https://github.com/adler-j/learned_primal_dual","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learned-primal-dual-reconstruction","repo_url":"https://github.com/alexdenker/htc2022_lpd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"ct-reconstruction","task_name":"CT Reconstruction"},{"task_slug":"unrolling","task_name":"Rolling Shutter Correction"},{"task_slug":"ssim","task_name":"SSIM"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.06474","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}