{"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/a-tensor-factorization-method-for-3d-super","title":"A Tensor Factorization Method for 3D Super-Resolution with Application to Dental CT","arxiv_id":"1807.10027","date":"2018-07-26","proceeding":null,"authors":["Janka Hatvani","Adrian Basarab","Jean-Yves Tourneret","Miklós Gyöngy","Denis Kouamé"],"abstract":"Available super-resolution techniques for 3D images are either\ncomputationally inefficient prior-knowledge-based iterative techniques or deep\nlearning methods which require a large database of known low- and\nhigh-resolution image pairs. A recently introduced tensor-factorization-based\napproach offers a fast solution without the use of known image pairs or strict\nprior assumptions. In this article this factorization framework is investigated\nfor single image resolution enhancement with an off-line estimate of the system\npoint spread function. The technique is applied to 3D cone beam computed\ntomography for dental image resolution enhancement. To demonstrate the\nefficiency of our method, it is compared to a recent state-of-the-art iterative\ntechnique using low-rank and total variation regularizations. In contrast to\nthis comparative technique, the proposed reconstruction technique gives a\n2-order-of-magnitude improvement in running time -- 2 minutes compared to 2\nhours for a dental volume of 282$\\times$266$\\times$392 voxels. Furthermore, it\nalso offers slightly improved quantitative results (peak signal-to-noise ratio,\nsegmentation quality). Another advantage of the presented technique is the low\nnumber of hyperparameters. As demonstrated in this paper, the framework is not\nsensitive to small changes of its parameters, proposing an ease of use.","url_abs":"http://arxiv.org/abs/1807.10027v1","url_pdf":"http://arxiv.org/pdf/1807.10027v1.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":"a-tensor-factorization-method-for-3d-super","repo_url":"https://bitbucket.org/fengshi421/superresolutiontoolkit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}