CameraPose:利用野外2D注释的弱监督单目3D人体姿势估计

Cheng-Yen Yang, Jiajia Luo, Lu Xia, Yuyin Sun, Nan Qiao, Ke Zhang, Zhongyu Jiang, Jenq-Neng Hwang
{"title":"CameraPose:利用野外2D注释的弱监督单目3D人体姿势估计","authors":"Cheng-Yen Yang, Jiajia Luo, Lu Xia, Yuyin Sun, Nan Qiao, Ke Zhang, Zhongyu Jiang, Jenq-Neng Hwang","doi":"10.1109/WACV56688.2023.00294","DOIUrl":null,"url":null,"abstract":"To improve the generalization of 3D human pose estimators, many existing deep learning based models focus on adding different augmentations to training poses. However, data augmentation techniques are limited to the \"seen\" pose combinations and hard to infer poses with rare \"unseen\" joint positions. To address this problem, we present CameraPose, a weakly-supervised framework for 3D human pose estimation from a single image, which can not only be applied on 2D-3D pose pairs but also on 2D alone annotations. By adding a camera parameter branch, any in-the-wild 2D annotations can be fed into our pipeline to boost the training diversity and the 3D poses can be implicitly learned by reprojecting back to 2D. Moreover, CameraPose introduces a refinement network module with confidence-guided loss to further improve the quality of noisy 2D keypoints extracted by 2D pose estimators. Experimental results demonstrate that the CameraPose brings in clear improvements on cross-scenario datasets. Notably, it outperforms the baseline method by 3mm on the most challenging dataset 3DPW. In addition, by combining our proposed refinement network module with existing 3D pose estimators, their performance can be improved in cross-scenario evaluation.","PeriodicalId":270631,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations\",\"authors\":\"Cheng-Yen Yang, Jiajia Luo, Lu Xia, Yuyin Sun, Nan Qiao, Ke Zhang, Zhongyu Jiang, Jenq-Neng Hwang\",\"doi\":\"10.1109/WACV56688.2023.00294\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To improve the generalization of 3D human pose estimators, many existing deep learning based models focus on adding different augmentations to training poses. However, data augmentation techniques are limited to the \\\"seen\\\" pose combinations and hard to infer poses with rare \\\"unseen\\\" joint positions. To address this problem, we present CameraPose, a weakly-supervised framework for 3D human pose estimation from a single image, which can not only be applied on 2D-3D pose pairs but also on 2D alone annotations. By adding a camera parameter branch, any in-the-wild 2D annotations can be fed into our pipeline to boost the training diversity and the 3D poses can be implicitly learned by reprojecting back to 2D. Moreover, CameraPose introduces a refinement network module with confidence-guided loss to further improve the quality of noisy 2D keypoints extracted by 2D pose estimators. Experimental results demonstrate that the CameraPose brings in clear improvements on cross-scenario datasets. Notably, it outperforms the baseline method by 3mm on the most challenging dataset 3DPW. In addition, by combining our proposed refinement network module with existing 3D pose estimators, their performance can be improved in cross-scenario evaluation.\",\"PeriodicalId\":270631,\"journal\":{\"name\":\"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WACV56688.2023.00294\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WACV56688.2023.00294","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

为了提高三维人体姿态估计器的泛化能力,许多现有的基于深度学习的模型都侧重于在训练姿态中添加不同的增强。然而,数据增强技术仅限于“可见”的姿势组合,很难推断出罕见的“不可见”关节位置的姿势。为了解决这个问题,我们提出了CameraPose,这是一个弱监督框架,用于从单张图像估计3D人体姿势,它不仅可以应用于2D-3D姿势对,还可以应用于2D单独的注释。通过添加相机参数分支,任何野外2D注释都可以馈送到我们的管道中,以提高训练的多样性,3D姿势可以通过重新投影回2D来隐式学习。此外,CameraPose引入了一个带有置信度引导损失的细化网络模块,以进一步提高2D姿态估计器提取的有噪声2D关键点的质量。实验结果表明,CameraPose在跨场景数据集上有明显的改进。值得注意的是,在最具挑战性的数据集3DPW上,它的性能比基线方法高3mm。此外,通过将我们提出的改进网络模块与现有的3D姿态估计器相结合,可以提高它们在跨场景评估中的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations
To improve the generalization of 3D human pose estimators, many existing deep learning based models focus on adding different augmentations to training poses. However, data augmentation techniques are limited to the "seen" pose combinations and hard to infer poses with rare "unseen" joint positions. To address this problem, we present CameraPose, a weakly-supervised framework for 3D human pose estimation from a single image, which can not only be applied on 2D-3D pose pairs but also on 2D alone annotations. By adding a camera parameter branch, any in-the-wild 2D annotations can be fed into our pipeline to boost the training diversity and the 3D poses can be implicitly learned by reprojecting back to 2D. Moreover, CameraPose introduces a refinement network module with confidence-guided loss to further improve the quality of noisy 2D keypoints extracted by 2D pose estimators. Experimental results demonstrate that the CameraPose brings in clear improvements on cross-scenario datasets. Notably, it outperforms the baseline method by 3mm on the most challenging dataset 3DPW. In addition, by combining our proposed refinement network module with existing 3D pose estimators, their performance can be improved in cross-scenario evaluation.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信