{"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/cubeslam-monocular-3d-object-detection-and","title":"CubeSLAM: Monocular 3D Object SLAM","arxiv_id":"1806.00557","date":"2018-06-01","proceeding":null,"authors":["Shichao Yang","Sebastian Scherer"],"abstract":"We present a method for single image 3D cuboid object detection and\nmulti-view object SLAM in both static and dynamic environments, and demonstrate\nthat the two parts can improve each other. Firstly for single image object\ndetection, we generate high-quality cuboid proposals from 2D bounding boxes and\nvanishing points sampling. The proposals are further scored and selected based\non the alignment with image edges. Secondly, multi-view bundle adjustment with\nnew object measurements is proposed to jointly optimize poses of cameras,\nobjects and points. Objects can provide long-range geometric and scale\nconstraints to improve camera pose estimation and reduce monocular drift.\nInstead of treating dynamic regions as outliers, we utilize object\nrepresentation and motion model constraints to improve the camera pose\nestimation. The 3D detection experiments on SUN RGBD and KITTI show better\naccuracy and robustness over existing approaches. On the public TUM, KITTI\nodometry and our own collected datasets, our SLAM method achieves the\nstate-of-the-art monocular camera pose estimation and at the same time,\nimproves the 3D object detection accuracy.","url_abs":"http://arxiv.org/abs/1806.00557v2","url_pdf":"http://arxiv.org/pdf/1806.00557v2.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":"cubeslam-monocular-3d-object-detection-and","repo_url":"https://github.com/shichaoy/cube_slam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"cubeslam-monocular-3d-object-detection-and","repo_url":"https://github.com/shichaoy/cuboid_detect","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"cubeslam-monocular-3d-object-detection-and","repo_url":"https://github.com/shichaoy/matlab_cuboid_detect","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"cubeslam-monocular-3d-object-detection-and","repo_url":"https://github.com/tiev-tongji/quadric_slam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"cubeslam-monocular-3d-object-detection-and","repo_url":"https://github.com/wuxiaolang/Cube_SLAM_wu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"camera-pose-estimation","task_name":"Camera Pose Estimation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-slam","task_name":"Object SLAM"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.00557","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}