{"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/towards-viewpoint-invariant-3d-human-pose","title":"Towards Viewpoint Invariant 3D Human Pose Estimation","arxiv_id":"1603.07076","date":"2016-03-23","proceeding":null,"authors":["Albert Haque","Boya Peng","Zelun Luo","Alexandre Alahi","Serena Yeung","Li Fei-Fei"],"abstract":"We propose a viewpoint invariant model for 3D human pose estimation from a\nsingle depth image. To achieve this, our discriminative model embeds local\nregions into a learned viewpoint invariant feature space. Formulated as a\nmulti-task learning problem, our model is able to selectively predict partial\nposes in the presence of noise and occlusion. Our approach leverages a\nconvolutional and recurrent network architecture with a top-down error feedback\nmechanism to self-correct previous pose estimates in an end-to-end manner. We\nevaluate our model on a previously published depth dataset and a newly\ncollected human pose dataset containing 100K annotated depth images from\nextreme viewpoints. Experiments show that our model achieves competitive\nperformance on frontal views while achieving state-of-the-art performance on\nalternate viewpoints.","url_abs":"http://arxiv.org/abs/1603.07076v3","url_pdf":"http://arxiv.org/pdf/1603.07076v3.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":"towards-viewpoint-invariant-3d-human-pose","repo_url":"https://github.com/mks0601/V2V-PoseNet_RELEASE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"towards-viewpoint-invariant-3d-human-pose","repo_url":"https://github.com/zhengkang86/ram_person_id","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[{"slug":"itop","name":"ITOP","full_name":"Invariant-Top View Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-itop-front-view","task":"Pose Estimation","dataset":"ITOP front-view","model":"Multi-task learning + viewpoint invariance","rank_in_archive_order":7,"of":7,"metrics":{"Mean mAP":"77.4"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-itop-top-view","task":"Pose Estimation","dataset":"ITOP top-view","model":"Multi-task learning + viewpoint invariance","rank_in_archive_order":4,"of":5,"metrics":{"Mean mAP":"75.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}