{"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/inloc-indoor-visual-localization-with-dense","title":"InLoc: Indoor Visual Localization with Dense Matching and View Synthesis","arxiv_id":"1803.10368","date":"2018-03-28","proceeding":"CVPR 2018 6","authors":["Hajime Taira","Masatoshi Okutomi","Torsten Sattler","Mircea Cimpoi","Marc Pollefeys","Josef Sivic","Tomas Pajdla","Akihiko Torii"],"abstract":"We seek to predict the 6 degree-of-freedom (6DoF) pose of a query photograph\nwith respect to a large indoor 3D map. The contributions of this work are\nthree-fold. First, we develop a new large-scale visual localization method\ntargeted for indoor environments. The method proceeds along three steps: (i)\nefficient retrieval of candidate poses that ensures scalability to large-scale\nenvironments, (ii) pose estimation using dense matching rather than local\nfeatures to deal with textureless indoor scenes, and (iii) pose verification by\nvirtual view synthesis to cope with significant changes in viewpoint, scene\nlayout, and occluders. Second, we collect a new dataset with reference 6DoF\nposes for large-scale indoor localization. Query photographs are captured by\nmobile phones at a different time than the reference 3D map, thus presenting a\nrealistic indoor localization scenario. Third, we demonstrate that our method\nsignificantly outperforms current state-of-the-art indoor localization\napproaches on this new challenging data.","url_abs":"http://arxiv.org/abs/1803.10368v2","url_pdf":"http://arxiv.org/pdf/1803.10368v2.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":"inloc-indoor-visual-localization-with-dense","repo_url":"https://github.com/HajimeTaira/InLoc_demo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"indoor-localization","task_name":"Indoor Localization"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"visual-localization","task_name":"Visual Localization"}],"methods":[],"datasets_introduced":[{"slug":"inloc","name":"InLoc","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}