{"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/unsupervised-learning-for-fast-probabilistic","title":"Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration","arxiv_id":"1805.04605","date":"2018-05-11","proceeding":null,"authors":["Adrian V. Dalca","Guha Balakrishnan","John Guttag","Mert R. Sabuncu"],"abstract":"Traditional deformable registration techniques achieve impressive results and\noffer a rigorous theoretical treatment, but are computationally intensive since\nthey solve an optimization problem for each image pair. Recently,\nlearning-based methods have facilitated fast registration by learning spatial\ndeformation functions. However, these approaches use restricted deformation\nmodels, require supervised labels, or do not guarantee a diffeomorphic\n(topology-preserving) registration. Furthermore, learning-based registration\ntools have not been derived from a probabilistic framework that can offer\nuncertainty estimates. In this paper, we present a probabilistic generative\nmodel and derive an unsupervised learning-based inference algorithm that makes\nuse of recent developments in convolutional neural networks (CNNs). We\ndemonstrate our method on a 3D brain registration task, and provide an\nempirical analysis of the algorithm. Our approach results in state of the art\naccuracy and very fast runtimes, while providing diffeomorphic guarantees and\nuncertainty estimates. Our implementation is available online at\nhttp://voxelmorph.csail.mit.edu .","url_abs":"http://arxiv.org/abs/1805.04605v2","url_pdf":"http://arxiv.org/pdf/1805.04605v2.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":"unsupervised-learning-for-fast-probabilistic","repo_url":"https://github.com/voxelmorph/voxelmorph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"unsupervised-learning-for-fast-probabilistic","repo_url":"https://github.com/CIG-UCL/polaffini","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unsupervised-learning-for-fast-probabilistic","repo_url":"https://github.com/yh854/Rigid-Registration-of-3D-MRI-Based-on-Unsupervised-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.04605","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}