Category Map Guided Ordinal Depth Prediction for 3D Human Pose Estimation | |
Liguo Jiang1,2; Juntao Ye1,3 | |
2021-03-02 | |
会议日期 | 2021-5-21 |
会议地点 | Xi'an, China |
英文摘要 | In this paper, we propose a two-stage method to estimate 3D human pose, which focuses on the uncertainty of lifting 2D detected pose to 3D pose. Firstly, a novel category map is introduced to predict the ordinal depth category which depicts three kinds of depth ordering relationship for linked joints. Compared with the common probability of vector, our category map can provide better association between prediction with image appearance, and lead to a higher classification accuracy. Secondly, taking predicted 2D pose and ordinal depth category as input, we put forward a temporal convolution network to regress 3D pose, which exploits the temporal context to alleviate the 2D-to-3D uncertainty and reduce prediction errors rate from single image further. Experimental results show that our method can outperform promising results on several benchmarks. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44932] |
专题 | 自动化研究所_模式识别国家重点实验室_机器人视觉团队 |
通讯作者 | Liguo Jiang |
作者单位 | 1.Institute of Automation 2.University of the Chinese Academy of Sciences 3.National Laboratory of Pattern Recognition |
推荐引用方式 GB/T 7714 | Liguo Jiang,Juntao Ye. Category Map Guided Ordinal Depth Prediction for 3D Human Pose Estimation[C]. 见:. Xi'an, China. 2021-5-21. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论