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

Benchmark Model Rank Results
3d-human-pose-estimation-on-humaneva-iGLA-GCN (T=27, GT)#1Mean Reconstruction Error (mm): 9.2
monocular-3d-human-pose-estimation-on-human3-6m-protocol-1-monocular-ground-truth-2dGLA-GCN (GT 2D, T=243, C_out=512, sequence reconstruction)#7MPJPE: 21.0
3d-human-pose-estimation-on-mpi-inf-3dhpGLA-GCN (T=81)#13MPJPE: 27.76AUC: 79.12PCK: 98.53
monocular-3d-human-pose-estimation-on-human3-6mGLA-GCN (CPN, T=243)#20Average MPJPE (mm): 44.4
3d-human-pose-estimation-on-human36mGLA-GCN (CPN, T=243)#76PA-MPJPE: 34.8