{"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/modelling-uncertainty-in-deep-learning-for","title":"Modelling Uncertainty in Deep Learning for Camera Relocalization","arxiv_id":"1509.05909","date":"2015-09-19","proceeding":null,"authors":["Alex Kendall","Roberto Cipolla"],"abstract":"We present a robust and real-time monocular six degree of freedom visual\nrelocalization system. We use a Bayesian convolutional neural network to\nregress the 6-DOF camera pose from a single RGB image. It is trained in an\nend-to-end manner with no need of additional engineering or graph optimisation.\nThe algorithm can operate indoors and outdoors in real time, taking under 6ms\nto compute. It obtains approximately 2m and 6 degrees accuracy for very large\nscale outdoor scenes and 0.5m and 10 degrees accuracy indoors. Using a Bayesian\nconvolutional neural network implementation we obtain an estimate of the\nmodel's relocalization uncertainty and improve state of the art localization\naccuracy on a large scale outdoor dataset. We leverage the uncertainty measure\nto estimate metric relocalization error and to detect the presence or absence\nof the scene in the input image. We show that the model's uncertainty is caused\nby images being dissimilar to the training dataset in either pose or\nappearance.","url_abs":"http://arxiv.org/abs/1509.05909v2","url_pdf":"http://arxiv.org/pdf/1509.05909v2.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":"modelling-uncertainty-in-deep-learning-for","repo_url":"https://github.com/alexgkendall/caffe-posenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"camera-relocalization","task_name":"Camera Relocalization"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1509.05909","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}