A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video

11 Mar 2020  ·  Junfa Liu, Juan Rojas, Zhijun Liang, Yihui Li, Yisheng Guan ·

Spatio-temporal information is key to resolve occlusion and depth ambiguity in 3D pose estimation. Previous methods have focused on either temporal contexts or local-to-global architectures that embed fixed-length spatio-temporal information. To date, there have not been effective proposals to simultaneously and flexibly capture varying spatio-temporal sequences and effectively achieves real-time 3D pose estimation. In this work, we improve the learning of kinematic constraints in the human skeleton: posture, local kinematic connections, and symmetry by modeling local and global spatial information via attention mechanisms. To adapt to single- and multi-frame estimation, the dilated temporal model is employed to process varying skeleton sequences. Also, importantly, we carefully design the interleaving of spatial semantics with temporal dependencies to achieve a synergistic effect. To this end, we propose a simple yet effective graph attention spatio-temporal convolutional network (GAST-Net) that comprises of interleaved temporal convolutional and graph attention blocks. Experiments on two challenging benchmark datasets (Human3.6M and HumanEva-I) and YouTube videos demonstrate that our approach effectively mitigates depth ambiguity and self-occlusion, generalizes to half upper body estimation, and achieves competitive performance on 2D-to-3D video pose estimation. Code, video, and supplementary information is available at: \href{http://www.juanrojas.net/gast/}{http://www.juanrojas.net/gast/}

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation Human3.6M GAST (T=81) Average MPJPE (mm) 45.7 # 118
PA-MPJPE 35.9 # 28
3D Human Pose Estimation Human3.6M GAST (T=27) Average MPJPE (mm) 46.2 # 121
PA-MPJPE 36 # 29
3D Human Pose Estimation Human3.6M GAST (T=9) Average MPJPE (mm) 49 # 148
PA-MPJPE 37.4 # 37
3D Human Pose Estimation HumanEva-I GAST Mean Reconstruction Error (mm) 21.2 # 11

Methods