{"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/metric-learning-for-image-registration","title":"Metric Learning for Image Registration","arxiv_id":"1904.09524","date":"2019-04-21","proceeding":"CVPR 2019 6","authors":["Marc Niethammer","Roland Kwitt","Francois-Xavier Vialard"],"abstract":"Image registration is a key technique in medical image analysis to estimate\ndeformations between image pairs. A good deformation model is important for\nhigh-quality estimates. However, most existing approaches use ad-hoc\ndeformation models chosen for mathematical convenience rather than to capture\nobserved data variation. Recent deep learning approaches learn deformation\nmodels directly from data. However, they provide limited control over the\nspatial regularity of transformations. Instead of learning the entire\nregistration approach, we learn a spatially-adaptive regularizer within a\nregistration model. This allows controlling the desired level of regularity and\npreserving structural properties of a registration model. For example,\ndiffeomorphic transformations can be attained. Our approach is a radical\ndeparture from existing deep learning approaches to image registration by\nembedding a deep learning model in an optimization-based registration algorithm\nto parameterize and data-adapt the registration model itself.","url_abs":"http://arxiv.org/abs/1904.09524v1","url_pdf":"http://arxiv.org/pdf/1904.09524v1.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":"metric-learning-for-image-registration","repo_url":"https://github.com/uncbiag/registration","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"deformable-medical-image-registration","task_name":"Deformable Medical Image Registration"},{"task_slug":"diffeomorphic-medical-image-registration","task_name":"Diffeomorphic Medical Image Registration"},{"task_slug":"image-registration","task_name":"Image Registration"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/diffeomorphic-medical-image-registration-on-2","task":"Diffeomorphic Medical Image Registration","dataset":"CUMC12","model":"Metric Net (Local Reg)","rank_in_archive_order":1,"of":3,"metrics":{"Mean target overlap ratio":"0.520"},"uses_additional_data":false},{"leaderboard":"/sota/diffeomorphic-medical-image-registration-on-2","task":"Diffeomorphic Medical Image Registration","dataset":"CUMC12","model":"Metric Net (Global Reg)","rank_in_archive_order":3,"of":3,"metrics":{"Mean target overlap ratio":"0.480"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.09524","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}