P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation

Benchmark Model Rank Results
monocular-3d-human-pose-estimation-on-human3-6m-protocol-1-monocular-ground-truth-2dP-STMO-S (243 frames)#10MPJPE: 29.3
3d-human-pose-estimation-on-human36mP-STMO (N=243)#12Average MPJPE (mm): 42.1Using 2D ground-truth joints: No…
3d-human-pose-estimation-on-human36mP-STMO-S (N=81)#22Average MPJPE (mm): 44.1Using 2D ground-truth joints: No…
monocular-3d-human-pose-estimation-on-human3-6mP-STMO (N=243)#14Average MPJPE (mm): 42.1Use Video Sequence: YesFrames Needed: 243…
3d-human-pose-estimation-on-mpi-inf-3dhpP-STMO (N=81)#18MPJPE: 32.2AUC: 75.8PCK: 97.9