{"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/benchmarking-6dof-outdoor-visual-localization","title":"Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions","arxiv_id":"1707.09092","date":"2017-07-28","proceeding":"CVPR 2018 6","authors":["Torsten Sattler","Will Maddern","Carl Toft","Akihiko Torii","Lars Hammarstrand","Erik Stenborg","Daniel Safari","Masatoshi Okutomi","Marc Pollefeys","Josef Sivic","Fredrik Kahl","Tomas Pajdla"],"abstract":"Visual localization enables autonomous vehicles to navigate in their\nsurroundings and augmented reality applications to link virtual to real worlds.\nPractical visual localization approaches need to be robust to a wide variety of\nviewing condition, including day-night changes, as well as weather and seasonal\nvariations, while providing highly accurate 6 degree-of-freedom (6DOF) camera\npose estimates. In this paper, we introduce the first benchmark datasets\nspecifically designed for analyzing the impact of such factors on visual\nlocalization. Using carefully created ground truth poses for query images taken\nunder a wide variety of conditions, we evaluate the impact of various factors\non 6DOF camera pose estimation accuracy through extensive experiments with\nstate-of-the-art localization approaches. Based on our results, we draw\nconclusions about the difficulty of different conditions, showing that\nlong-term localization is far from solved, and propose promising avenues for\nfuture work, including sequence-based localization approaches and the need for\nbetter local features. Our benchmark is available at visuallocalization.net.","url_abs":"http://arxiv.org/abs/1707.09092v3","url_pdf":"http://arxiv.org/pdf/1707.09092v3.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":"benchmarking-6dof-outdoor-visual-localization","repo_url":"https://github.com/ethz-asl/hf_net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"benchmarking-6dof-outdoor-visual-localization","repo_url":"https://github.com/ethz-asl/hfnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"camera-pose-estimation","task_name":"Camera Pose Estimation"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"visual-localization","task_name":"Visual Localization"}],"methods":[],"datasets_introduced":[{"slug":"aachen-day-night","name":"Aachen Day-Night","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.09092","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}