Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks

Benchmark Model Rank Results
3d-human-pose-estimation-on-human36mSTRGCN (T=7)#35Average MPJPE (mm): 48.8Using 2D ground-truth joints: No
3d-human-pose-estimation-on-human36mSTRGCN (T=3)#36Average MPJPE (mm): 49.1Using 2D ground-truth joints: No
3d-human-pose-estimation-on-human36mSTRGCN (T=1)#46Average MPJPE (mm): 50.6Using 2D ground-truth joints: No