{"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/bundletrack-6d-pose-tracking-for-novel","title":"BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models","arxiv_id":"2108.00516","date":"2021-08-01","proceeding":null,"authors":["Bowen Wen","Kostas Bekris"],"abstract":"Tracking the 6D pose of objects in video sequences is important for robot manipulation. Most prior efforts, however, often assume that the target object's CAD model, at least at a category-level, is available for offline training or during online template matching. This work proposes BundleTrack, a general framework for 6D pose tracking of novel objects, which does not depend upon 3D models, either at the instance or category-level. It leverages the complementary attributes of recent advances in deep learning for segmentation and robust feature extraction, as well as memory-augmented pose graph optimization for spatiotemporal consistency. This enables long-term, low-drift tracking under various challenging scenarios, including significant occlusions and object motions. Comprehensive experiments given two public benchmarks demonstrate that the proposed approach significantly outperforms state-of-art, category-level 6D tracking or dynamic SLAM methods. When compared against state-of-art methods that rely on an object instance CAD model, comparable performance is achieved, despite the proposed method's reduced information requirements. An efficient implementation in CUDA provides a real-time performance of 10Hz for the entire framework. Code is available at: https://github.com/wenbowen123/BundleTrack","url_abs":"https://arxiv.org/abs/2108.00516v1","url_pdf":"https://arxiv.org/pdf/2108.00516v1.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":"bundletrack-6d-pose-tracking-for-novel","repo_url":"https://github.com/wenbowen123/BundleTrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-object-tracking","task_name":"3D Object Tracking"},{"task_slug":"6d-pose-estimation-1","task_name":"6D Pose Estimation"},{"task_slug":"6d-pose-estimation","task_name":"6D Pose Estimation using RGB"},{"task_slug":"6d-pose-estimation-using-rgbd","task_name":"6D Pose Estimation using RGBD"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"pose-tracking","task_name":"Pose Tracking"},{"task_slug":"real-time-visual-tracking","task_name":"Real-Time Visual Tracking"},{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"},{"task_slug":"template-matching","task_name":"Template Matching"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/6d-pose-estimation-using-rgbd-on-real275","task":"6D Pose Estimation using RGBD","dataset":"REAL275","model":"BundleTrack","rank_in_archive_order":10,"of":11,"metrics":{"Rerr":"2.4","Terr":"2.1","mAP 3DIou@25":"99.9","mAP 5, 5cm":"87.4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2108.00516","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}