3D human pose estimation with multi-scale graph convolution and hierarchical body pooling

2021 ◽  
Author(s):  
Ke Huang ◽  
TianQi Sui ◽  
Hong Wu
Keyword(s):  
Pose Estimation ◽  
Human Pose Estimation ◽  
Multi Scale ◽  
Human Pose ◽  
3D Human Pose Estimation

scholarly journals PoseGTAC: Graph Transformer Encoder-Decoder with Atrous Convolution for 3D Human Pose Estimation

2021 ◽  
Author(s):  
Yiran Zhu ◽  
Xing Xu ◽  
Fumin Shen ◽  
Yanli Ji ◽  
Lianli Gao ◽  
...  
Keyword(s):  
Long Range ◽  
Pose Estimation ◽  
Contextual Information ◽  
Receptive Fields ◽  
Human Pose Estimation ◽  
Multi Scale ◽  
Single Scale ◽  
Human Pose ◽  
Graph Neural Networks ◽  
3D Human Pose Estimation

Graph neural networks (GNNs) have been widely used in the 3D human pose estimation task, since the pose representation of a human body can be naturally modeled by the graph structure. Generally, most of the existing GNN-based models utilize the restricted receptive fields of filters and single-scale information, while neglecting the valuable multi-scale contextual information. To tackle this issue, we propose a novel Graph Transformer Encoder-Decoder with Atrous Convolution, named PoseGTAC, to effectively extract multi-scale context and long-range information. In our proposed PoseGTAC model, Graph Atrous Convolution (GAC) and Graph Transformer Layer (GTL), respectively for the extraction of local multi-scale and global long-range information, are combined and stacked in an encoder-decoder structure, where graph pooling and unpooling are adopted for the interaction of multi-scale information from local to global (e.g., part-scale and body-scale). Extensive experiments on the Human3.6M and MPI-INF-3DHP datasets demonstrate that the proposed PoseGTAC model exceeds all previous methods and achieves state-of-the-art performance.

scholarly journals Deep 3D human pose estimation: A review

2021 ◽  
pp. 103225
Author(s):  
Jinbao Wang ◽  
Shujie Tan ◽  
Xiantong Zhen ◽  
Shuo Xu ◽  
Feng Zheng ◽  
...  
Keyword(s):  
Pose Estimation ◽  
Human Pose Estimation ◽  
Human Pose ◽  
3D Human Pose Estimation

scholarly journals A survey on monocular 3D human pose estimation

2020 ◽  
Vol 2 (6) ◽  
pp. 471-500
Author(s):  
Xiaopeng Ji ◽  
Qi Fang ◽  
Junting Dong ◽  
Qing Shuai ◽  
Wen Jiang ◽  
...  
Keyword(s):  
Pose Estimation ◽  
Human Pose Estimation ◽  
Human Pose ◽  
3D Human Pose Estimation
Sign in / Sign up

Export Citation Format

Share Document