{"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/3d-robot-pose-estimation-from-2d-images","title":"3D Robot Pose Estimation from 2D Images","arxiv_id":"1902.04987","date":"2019-02-13","proceeding":null,"authors":["Christoph Heindl","Sebastian Zambal","Thomas Ponitz","Andreas Pichler","Josef Scharinger"],"abstract":"This paper considers the task of locating articulated poses of multiple\nrobots in images. Our approach simultaneously infers the number of robots in a\nscene, identifies joint locations and estimates sparse depth maps around joint\nlocations. The proposed method applies staged convolutional feature detectors\nto 2D image inputs and computes robot instance masks using a recurrent network\narchitecture. In addition, regression maps of most likely joint locations in\npixel coordinates together with depth information are computed. Compositing 3D\nrobot joint kinematics is accomplished by applying masks to joint readout maps.\nOur end-to-end formulation is in contrast to previous work in which the\ncomposition of robot joints into kinematics is performed in a separate\npost-processing step. Despite the fact that our models are trained on\nartificial data, we demonstrate generalizability to real world images.","url_abs":"http://arxiv.org/abs/1902.04987v1","url_pdf":"http://arxiv.org/pdf/1902.04987v1.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":"3d-robot-pose-estimation-from-2d-images","repo_url":"https://github.com/cheind/robot-pose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"robot-pose-estimation","task_name":"Robot Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.04987","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}