{"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/recovering-affine-features-from-orientation","title":"Recovering affine features from orientation- and scale-invariant ones","arxiv_id":"1807.03503","date":"2018-07-10","proceeding":null,"authors":["Daniel Barath"],"abstract":"An approach is proposed for recovering affine correspondences (ACs) from\norientation- and scale-invariant, e.g. SIFT, features. The method calculates\nthe affine parameters consistent with a pre-estimated epipolar geometry from\nthe point coordinates and the scales and rotations which the feature detector\nobtains. The closed-form solution is given as the roots of a quadratic\npolynomial equation, thus having two possible real candidates and fast\nprocedure, i.e. <1 millisecond. It is shown, as a possible application, that\nusing the proposed algorithm allows us to estimate a homography for every\nsingle correspondence independently. It is validated both in our synthetic\nenvironment and on publicly available real world datasets, that the proposed\ntechnique leads to accurate ACs. Also, the estimated homographies have similar\naccuracy to what the state-of-the-art methods obtain, but due to requiring only\na single correspondence, the robust estimation, e.g. by locally optimized\nRANSAC, is an order of magnitude faster.","url_abs":"http://arxiv.org/abs/1807.03503v1","url_pdf":"http://arxiv.org/pdf/1807.03503v1.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":"recovering-affine-features-from-orientation","repo_url":"https://github.com/danini/recovering-affine-features","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.03503","atlas_url":"https://app.syntology.ai/?focus=1807.03503","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}