{"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/advio-an-authentic-dataset-for-visual","title":"ADVIO: An authentic dataset for visual-inertial odometry","arxiv_id":"1807.09828","date":"2018-07-25","proceeding":"ECCV 2018 9","authors":["Santiago Cortés","Arno Solin","Esa Rahtu","Juho Kannala"],"abstract":"The lack of realistic and open benchmarking datasets for pedestrian\nvisual-inertial odometry has made it hard to pinpoint differences in published\nmethods. Existing datasets either lack a full six degree-of-freedom\nground-truth or are limited to small spaces with optical tracking systems. We\ntake advantage of advances in pure inertial navigation, and develop a set of\nversatile and challenging real-world computer vision benchmark sets for\nvisual-inertial odometry. For this purpose, we have built a test rig equipped\nwith an iPhone, a Google Pixel Android phone, and a Google Tango device. We\nprovide a wide range of raw sensor data that is accessible on almost any\nmodern-day smartphone together with a high-quality ground-truth track. We also\ncompare resulting visual-inertial tracks from Google Tango, ARCore, and Apple\nARKit with two recent methods published in academic forums. The data sets cover\nboth indoor and outdoor cases, with stairs, escalators, elevators, office\nenvironments, a shopping mall, and metro station.","url_abs":"http://arxiv.org/abs/1807.09828v1","url_pdf":"http://arxiv.org/pdf/1807.09828v1.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":"advio-an-authentic-dataset-for-visual","repo_url":"https://github.com/AaltoVision/ADVIO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"}],"methods":[],"datasets_introduced":[{"slug":"advio","name":"ADVIO","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.09828","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}