{"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/190503706","title":"Accurate Visual Localization for Automotive Applications","arxiv_id":"1905.03706","date":"2019-05-01","proceeding":null,"authors":["Eli Brosh","Matan Friedmann","Ilan Kadar","Lev Yitzhak Lavy","Elad Levi","Shmuel Rippa","Yair Lempert","Bruno Fernandez-Ruiz","Roei Herzig","Trevor Darrell"],"abstract":"Accurate vehicle localization is a crucial step towards building effective\nVehicle-to-Vehicle networks and automotive applications. Yet standard grade GPS\ndata, such as that provided by mobile phones, is often noisy and exhibits\nsignificant localization errors in many urban areas. Approaches for accurate\nlocalization from imagery often rely on structure-based techniques, and thus\nare limited in scale and are expensive to compute. In this paper, we present a\nscalable visual localization approach geared for real-time performance. We\npropose a hybrid coarse-to-fine approach that leverages visual and GPS location\ncues. Our solution uses a self-supervised approach to learn a compact road\nimage representation. This representation enables efficient visual retrieval\nand provides coarse localization cues, which are fused with vehicle ego-motion\nto obtain high accuracy location estimates. As a benchmark to evaluate the\nperformance of our visual localization approach, we introduce a new large-scale\ndriving dataset based on video and GPS data obtained from a large-scale network\nof connected dash-cams. Our experiments confirm that our approach is highly\neffective in challenging urban environments, reducing localization error by an\norder of magnitude.","url_abs":"http://arxiv.org/abs/1905.03706v1","url_pdf":"http://arxiv.org/pdf/1905.03706v1.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":"190503706","repo_url":"https://github.com/getnexar/Nexar-Visual-Localization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"visual-localization","task_name":"Visual Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.03706","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}