Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video

Benchmark Model Rank Results
3d-human-pose-estimation-on-3dpwMPS-Net (T=16)–MPVPE: 99.7PA-MPJPE: 52.1MPJPE: 84.3Acceleration Error: 7.4…
3d-human-pose-estimation-on-mpi-inf-3dhpMPS-Net (T=16)–MPJPE: 96.7PA-MPJPE: 62.8Acceleration Error: 9.6