{"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/unsupervised-geometry-aware-representation","title":"Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation","arxiv_id":"1804.01110","date":"2018-04-03","proceeding":"ECCV 2018 9","authors":["Helge Rhodin","Mathieu Salzmann","Pascal Fua"],"abstract":"Modern 3D human pose estimation techniques rely on deep networks, which\nrequire large amounts of training data. While weakly-supervised methods require\nless supervision, by utilizing 2D poses or multi-view imagery without\nannotations, they still need a sufficiently large set of samples with 3D\nannotations for learning to succeed.\n  In this paper, we propose to overcome this problem by learning a\ngeometry-aware body representation from multi-view images without annotations.\nTo this end, we use an encoder-decoder that predicts an image from one\nviewpoint given an image from another viewpoint. Because this representation\nencodes 3D geometry, using it in a semi-supervised setting makes it easier to\nlearn a mapping from it to 3D human pose. As evidenced by our experiments, our\napproach significantly outperforms fully-supervised methods given the same\namount of labeled data, and improves over other semi-supervised methods while\nusing as little as 1% of the labeled data.","url_abs":"http://arxiv.org/abs/1804.01110v1","url_pdf":"http://arxiv.org/pdf/1804.01110v1.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":"unsupervised-geometry-aware-representation","repo_url":"https://github.com/hrhodin/UnsupervisedGeometryAwareRepresentationLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"unsupervised-geometry-aware-representation","repo_url":"https://github.com/mattiagaggi/3D-Pose-Estimator---MSc_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-geometry","task_name":"3D geometry"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"weakly-supervised-3d-human-pose-estimation","task_name":"Weakly-supervised 3D Human Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-3d-human-pose-estimation-on","task":"Weakly-supervised 3D Human Pose Estimation","dataset":"Human3.6M","model":"Rhodin et al.","rank_in_archive_order":29,"of":33,"metrics":{"3D Annotations":"S1","Average MPJPE (mm)":"131.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.01110","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}