GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video

3D human pose estimation has been researched for decades with promising fruits. 3D human pose lifting is one of the promising research directions toward the task where both estimated pose and ground truth pose data are used for training. Existing pose lifting works mainly focus on improving the performance of estimated pose, but they usually underperform when testing on the ground truth pose data. We observe that the performance of the estimated pose can be easily improved by preparing good quality 2D pose, such as fine-tuning the 2D pose or using advanced 2D pose detectors. As such, we concentrate on improving the 3D human pose lifting via ground truth data for the future improvement of more quality estimated pose data. Towards this goal, a simple yet effective model called Global-local Adaptive Graph Convolutional Network (GLA-GCN) is proposed in this work. Our GLA-GCN globally models the spatiotemporal structure via a graph representation and backtraces local joint features for 3D human pose estimation via individually connected layers. To validate our model design, we conduct extensive experiments on three benchmark datasets: Human3.6M, HumanEva-I, and MPI-INF-3DHP. Experimental results show that our GLA-GCN implemented with ground truth 2D poses significantly outperforms state-of-the-art methods (e.g., up to around 3%, 17%, and 14% error reductions on Human3.6M, HumanEva-I, and MPI-INF-3DHP, respectively). GitHub: https://github.com/bruceyo/GLA-GCN.

PDF Abstract ICCV 2023 PDF ICCV 2023 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation Human3.6M GLA-GCN (T=243, GT) Average MPJPE (mm) 21.0 # 11
Using 2D ground-truth joints Yes # 2
Multi-View or Monocular Monocular # 1
3D Human Pose Estimation Human3.6M GLA-GCN (T=243, CPN) Average MPJPE (mm) 44.4 # 102
3D Human Pose Estimation HumanEva-I GLA-GCN (T=27, GT) Mean Reconstruction Error (mm) 9.2 # 1
3D Human Pose Estimation MPI-INF-3DHP GLA-GCN (T=81) AUC 79.12 # 7
MPJPE 27.76 # 7
PCK 99.53 # 1

Methods