{"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/6-dof-object-pose-from-semantic-keypoints","title":"6-DoF Object Pose from Semantic Keypoints","arxiv_id":"1703.04670","date":"2017-03-14","proceeding":null,"authors":["Georgios Pavlakos","Xiaowei Zhou","Aaron Chan","Konstantinos G. Derpanis","Kostas Daniilidis"],"abstract":"This paper presents a novel approach to estimating the continuous six degree\nof freedom (6-DoF) pose (3D translation and rotation) of an object from a\nsingle RGB image. The approach combines semantic keypoints predicted by a\nconvolutional network (convnet) with a deformable shape model. Unlike prior\nwork, we are agnostic to whether the object is textured or textureless, as the\nconvnet learns the optimal representation from the available training image\ndata. Furthermore, the approach can be applied to instance- and class-based\npose recovery. Empirically, we show that the proposed approach can accurately\nrecover the 6-DoF object pose for both instance- and class-based scenarios with\na cluttered background. For class-based object pose estimation,\nstate-of-the-art accuracy is shown on the large-scale PASCAL3D+ dataset.","url_abs":"http://arxiv.org/abs/1703.04670v1","url_pdf":"http://arxiv.org/pdf/1703.04670v1.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":"6-dof-object-pose-from-semantic-keypoints","repo_url":"https://github.com/geopavlakos/object3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keypoint-detection-on-pascal3d","task":"Keypoint Detection","dataset":"Pascal3D+","model":"ConvNet + deformable shape model","rank_in_archive_order":1,"of":4,"metrics":{"Mean PCK":"82.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.04670","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}