{"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/dynaslam-tracking-mapping-and-inpainting-in","title":"DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes","arxiv_id":"1806.05620","date":"2018-06-14","proceeding":null,"authors":["Berta Bescos","José M. Fácil","Javier Civera","José Neira"],"abstract":"The assumption of scene rigidity is typical in SLAM algorithms. Such a strong\nassumption limits the use of most visual SLAM systems in populated real-world\nenvironments, which are the target of several relevant applications like\nservice robotics or autonomous vehicles. In this paper we present DynaSLAM, a\nvisual SLAM system that, building over ORB-SLAM2 [1], adds the capabilities of\ndynamic object detection and background inpainting. DynaSLAM is robust in\ndynamic scenarios for monocular, stereo and RGB-D configurations. We are\ncapable of detecting the moving objects either by multi-view geometry, deep\nlearning or both. Having a static map of the scene allows inpainting the frame\nbackground that has been occluded by such dynamic objects. We evaluate our\nsystem in public monocular, stereo and RGB-D datasets. We study the impact of\nseveral accuracy/speed trade-offs to assess the limits of the proposed\nmethodology. DynaSLAM outperforms the accuracy of standard visual SLAM\nbaselines in highly dynamic scenarios. And it also estimates a map of the\nstatic parts of the scene, which is a must for long-term applications in\nreal-world environments.","url_abs":"http://arxiv.org/abs/1806.05620v2","url_pdf":"http://arxiv.org/pdf/1806.05620v2.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":"dynaslam-tracking-mapping-and-inpainting-in","repo_url":"https://github.com/BertaBescos/DynaSLAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"dynaslam-tracking-mapping-and-inpainting-in","repo_url":"https://github.com/JinfengZhang1994/DynaSLAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"dynaslam-tracking-mapping-and-inpainting-in","repo_url":"https://github.com/Skywalker666666/DynaSLAM_4DVD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"dynaslam-tracking-mapping-and-inpainting-in","repo_url":"https://github.com/liguolinhit/DynaSLAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"dynaslam-tracking-mapping-and-inpainting-in","repo_url":"https://github.com/linmeeka/semanticSlam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"dynaslam-tracking-mapping-and-inpainting-in","repo_url":"https://github.com/linmeeka/slamProject","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"dynaslam-tracking-mapping-and-inpainting-in","repo_url":"https://github.com/shuchun1997/Dynamic_slam-orbslam-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"orb-slam2","method_name":"ORB-SLAM2"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.05620","atlas_url":"https://app.syntology.ai/?focus=1806.05620","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}