{"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/captra-category-level-pose-tracking-for-rigid","title":"CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds","arxiv_id":"2104.03437","date":"2021-04-08","proceeding":"ICCV 2021 10","authors":["Yijia Weng","He Wang","Qiang Zhou","Yuzhe Qin","Yueqi Duan","Qingnan Fan","Baoquan Chen","Hao Su","Leonidas J. Guibas"],"abstract":"In this work, we tackle the problem of category-level online pose tracking of objects from point cloud sequences. For the first time, we propose a unified framework that can handle 9DoF pose tracking for novel rigid object instances as well as per-part pose tracking for articulated objects from known categories. Here the 9DoF pose, comprising 6D pose and 3D size, is equivalent to a 3D amodal bounding box representation with free 6D pose. Given the depth point cloud at the current frame and the estimated pose from the last frame, our novel end-to-end pipeline learns to accurately update the pose. Our pipeline is composed of three modules: 1) a pose canonicalization module that normalizes the pose of the input depth point cloud; 2) RotationNet, a module that directly regresses small interframe delta rotations; and 3) CoordinateNet, a module that predicts the normalized coordinates and segmentation, enabling analytical computation of the 3D size and translation. Leveraging the small pose regime in the pose-canonicalized point clouds, our method integrates the best of both worlds by combining dense coordinate prediction and direct rotation regression, thus yielding an end-to-end differentiable pipeline optimized for 9DoF pose accuracy (without using non-differentiable RANSAC). Our extensive experiments demonstrate that our method achieves new state-of-the-art performance on category-level rigid object pose (NOCS-REAL275) and articulated object pose benchmarks (SAPIEN, BMVC) at the fastest FPS ~12.","url_abs":"https://arxiv.org/abs/2104.03437v2","url_pdf":"https://arxiv.org/pdf/2104.03437v2.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":"captra-category-level-pose-tracking-for-rigid","repo_url":"https://github.com/HalfSummer11/CAPTRA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"pose-tracking","task_name":"Pose Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.03437","atlas_url":"https://app.syntology.ai/?focus=2104.03437","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}