{"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/semi-supervised-3d-hand-object-poses","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","arxiv_id":"2106.05266","date":"2021-06-09","proceeding":"CVPR 2021 1","authors":["Shaowei Liu","Hanwen Jiang","Jiarui Xu","Sifei Liu","Xiaolong Wang"],"abstract":"Estimating 3D hand and object pose from a single image is an extremely challenging problem: hands and objects are often self-occluded during interactions, and the 3D annotations are scarce as even humans cannot directly label the ground-truths from a single image perfectly. To tackle these challenges, we propose a unified framework for estimating the 3D hand and object poses with semi-supervised learning. We build a joint learning framework where we perform explicit contextual reasoning between hand and object representations by a Transformer. Going beyond limited 3D annotations in a single image, we leverage the spatial-temporal consistency in large-scale hand-object videos as a constraint for generating pseudo labels in semi-supervised learning. Our method not only improves hand pose estimation in challenging real-world dataset, but also substantially improve the object pose which has fewer ground-truths per instance. By training with large-scale diverse videos, our model also generalizes better across multiple out-of-domain datasets. Project page and code: https://stevenlsw.github.io/Semi-Hand-Object","url_abs":"https://arxiv.org/abs/2106.05266v1","url_pdf":"https://arxiv.org/pdf/2106.05266v1.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":"semi-supervised-3d-hand-object-poses","repo_url":"https://github.com/stevenlsw/Semi-Hand-Object","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-hand-pose-estimation","task_name":"3D Hand Pose Estimation"},{"task_slug":"hand-pose-estimation","task_name":"Hand Pose Estimation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"hand-object-pose","task_name":"hand-object pose"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-hand-pose-estimation-on-dexycb","task":"3D Hand Pose Estimation","dataset":"DexYCB","model":"SHO","rank_in_archive_order":9,"of":11,"metrics":{"Average MPJPE (mm)":"15.2","MPVPE":"-","PA-MPVPE":"-","PA-VAUC":"-","Procrustes-Aligned MPJPE":"6.58","VAUC":"-"},"uses_additional_data":false},{"leaderboard":"/sota/3d-hand-pose-estimation-on-ho-3d","task":"3D Hand Pose Estimation","dataset":"HO-3D v2","model":"SHO","rank_in_archive_order":15,"of":24,"metrics":{"PA-MPJPE (mm)":"10.1"},"uses_additional_data":false},{"leaderboard":"/sota/hand-object-pose-on-ho-3d","task":"hand-object pose","dataset":"HO-3D v2","model":"SHO","rank_in_archive_order":7,"of":9,"metrics":{"ADD-S":"-","Average MPJPE (mm)":"-","OME":"-","PA-MPJPE":"10.1","ST-MPJPE":"31.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.05266","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}