{"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/omniglue-generalizable-feature-matching-with","title":"OmniGlue: Generalizable Feature Matching with Foundation Model Guidance","arxiv_id":"2405.12979","date":"2024-05-21","proceeding":"CVPR 2024 1","authors":["Hanwen Jiang","Arjun Karpur","Bingyi Cao","QiXing Huang","Andre Araujo"],"abstract":"The image matching field has been witnessing a continuous emergence of novel learnable feature matching techniques, with ever-improving performance on conventional benchmarks. However, our investigation shows that despite these gains, their potential for real-world applications is restricted by their limited generalization capabilities to novel image domains. In this paper, we introduce OmniGlue, the first learnable image matcher that is designed with generalization as a core principle. OmniGlue leverages broad knowledge from a vision foundation model to guide the feature matching process, boosting generalization to domains not seen at training time. Additionally, we propose a novel keypoint position-guided attention mechanism which disentangles spatial and appearance information, leading to enhanced matching descriptors. We perform comprehensive experiments on a suite of $7$ datasets with varied image domains, including scene-level, object-centric and aerial images. OmniGlue's novel components lead to relative gains on unseen domains of $20.9\\%$ with respect to a directly comparable reference model, while also outperforming the recent LightGlue method by $9.5\\%$ relatively.Code and model can be found at https://hwjiang1510.github.io/OmniGlue","url_abs":"https://arxiv.org/abs/2405.12979v1","url_pdf":"https://arxiv.org/pdf/2405.12979v1.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":"omniglue-generalizable-feature-matching-with","repo_url":"https://github.com/google-research/omniglue","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.12979","atlas_url":"https://app.syntology.ai/?focus=2405.12979","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}