Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos

Benchmark Model Rank Results
3d-absolute-human-pose-estimation-on-human36mGnTCN#1MRPE: 88.1
3d-human-pose-estimation-on-3dpwGnTCN#64PA-MPJPE: 64.2
3d-human-pose-estimation-on-human36mGnTCN#9Average MPJPE (mm): 40.9Using 2D ground-truth joints: No
3d-multi-person-pose-estimation-absolute-on-mupotsGnTCN#23DPCK: 45.7
3d-multi-person-pose-estimation-root-relativeGnTCN#33DPCK: 87.5