Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation

Benchmark Model Rank Results
3d-human-pose-estimation-on-human36mMTF-Transformer (M=0.4, T=1)Average MPJPE (mm): 29.4Using 2D ground-truth joints: No
3d-human-pose-estimation-on-human36mMTF-Transformer (M=0.4, T=1, N=1)Average MPJPE (mm): 50.7Using 2D ground-truth joints: No
3d-human-pose-estimation-on-human36mMTF-Transformer (M=0.4, T=7)Average MPJPE (mm): 28.5Using 2D ground-truth joints: No
3d-human-pose-estimation-on-human36mMTF-Transformer (M=0.4, T=7, N=1)Average MPJPE (mm): 49.4Using 2D ground-truth joints: No
3d-human-pose-estimation-on-total-captureMTF-Transformer (M=0.4, T=7)Average MPJPE (mm): 29.2