{"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/optimal-multi-view-correction-of-local-affine","title":"Optimal Multi-view Correction of Local Affine Frames","arxiv_id":"1905.00519","date":"2019-05-01","proceeding":null,"authors":["Ivan Eichhardt","Daniel Barath"],"abstract":"The technique requires the epipolar geometry to be pre-estimated between each\nimage pair. It exploits the constraints which the camera movement implies, in\norder to apply a closed-form correction to the parameters of the input\naffinities. Also, it is shown that the rotations and scales obtained by\npartially affine-covariant detectors, e.g., AKAZE or SIFT, can be completed to\nbe full affine frames by the proposed algorithm. It is validated both in\nsynthetic experiments and on publicly available real-world datasets that the\nmethod always improves the output of the evaluated affine-covariant feature\ndetectors. As a by-product, these detectors are compared and the ones obtaining\nthe most accurate affine frames are reported. For demonstrating the\napplicability, we show that the proposed technique as a pre-processing step\nimproves the accuracy of pose estimation for a camera rig, surface normal and\nhomography estimation.","url_abs":"http://arxiv.org/abs/1905.00519v1","url_pdf":"http://arxiv.org/pdf/1905.00519v1.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":"optimal-multi-view-correction-of-local-affine","repo_url":"https://github.com/eivan/multiview-LAFs-correction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"homography-estimation","task_name":"Homography Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.00519","atlas_url":"https://app.syntology.ai/?focus=1905.00519","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}