Temporal-Aware Refinement for Video-based Human Pose and Shape Recovery

Open paper
Benchmark Model Rank Results
3d-human-pose-estimation-on-3dpwTAR (N=9)–MPVPE: 74.4PA-MPJPE: 40.6MPJPE: 62.7Acceleration Error: 7.7
3d-human-pose-estimation-on-mpi-inf-3dhpTAR (N=9)–MPJPE: 85.9PA-MPJPE: 60.5Acceleration Error: 9.2

Rank counts only results with a code link.