3D Human Pose Estimation on Human3.6M (test)
1.3MPJPE (Average)LiftFormer
Evaluation results
| Method | Links | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LiftFormern=2432020.09 | 1.3 | 1.3 | 1.4 | 1 | 1.6 | 1.1 | 1.3 | 1.3 | 1.6 | 0.9 | 1.2 | 1 | 1.2 | 1.9 | 1.6 | 1.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UGCN2D Detector=GT, Motion Loss=true2020.04 | 1.4 | 1.2 | 1.3 | 1.1 | 1.4 | 1.1 | 1.4 | 1.2 | 1.4 | 1 | 1.3 | 1 | 1.1 | 1.7 | 1.3 | 1.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LiftFormern=812020.09 | 1.4 | 1.4 | 1.5 | 1.1 | 1.7 | 1.1 | 1.4 | 1.4 | 1.7 | 0.9 | 1.3 | 1.1 | 1.2 | 2 | 1.7 | 1.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LiftFormern=272020.09 | 1.6 | 1.6 | 1.7 | 1.3 | 1.9 | 1.3 | 1.5 | 1.6 | 1.8 | 1 | 1.4 | 1.2 | 1.5 | 2.2 | 1.9 | 1.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MotionBERTT=243, mode=finetune, architecture=spatio-temporal Transformer2022.10 | 1.7 | 1.7 | 1.9 | 1.4 | 1.9 | 1.4 | 1.7 | 1.7 | 1.9 | 1.1 | 1.6 | 1.4 | 1.3 | 2.4 | 1.9 | 1.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MotionBERTT=243, mode=scratch, architecture=spatio-temporal Transformer2022.10 | 1.8 | 1.8 | 2.1 | 1.5 | 2 | 1.5 | 1.9 | 1.8 | 2.1 | 1.2 | 1.8 | 1.5 | 1.4 | 2.6 | 2 | 1.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UGCN2D Detector=CPN, Motion Loss=true2020.04 | 2.3 | 2.3 | 2.5 | 2 | 2.7 | 2 | 2.3 | 2.2 | 2.5 | 1.8 | 2.7 | 1.9 | 2 | 3.1 | 2.2 | 2.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTET=243, 2D detector=HRNet, architecture=spatio-temporal Transformer2022.10 | 2.3 | 2.5 | 2.7 | 1.9 | 2.8 | 1.9 | 2.2 | 2.3 | 2.6 | 1.6 | 2.2 | 1.9 | 2 | 3.1 | 2.6 | 2.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Chen et al.Frames=243, 2D Detector=CPN2021.06 | 2.5 | 2.7 | 2.8 | 2 | 3.1 | 2 | 2.4 | 2.4 | 2.8 | 1.8 | 2.4 | 2 | 2.1 | 3.4 | 2.7 | 2.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Virtual BonesFrames=243, 2D Detector=CPN2021.06 | 2.5 | 2.7 | 2.8 | 2 | 3.1 | 2 | 2.4 | 2.4 | 2.7 | 1.8 | 2.4 | 2 | 2.1 | 3.3 | 2.7 | 2.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Lin2020.04 | 2.7 | 2.7 | 2.8 | 2.1 | 3.1 | 2 | 2.5 | 2.7 | 2.9 | 1.8 | 2.6 | 2.1 | 2.3 | 3.7 | 2.7 | 3.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Pavllo2020.04 | 2.8 | 3 | 3.1 | 2.2 | 3.4 | 2.3 | 2.7 | 2.7 | 3.1 | 2.1 | 2.9 | 2.3 | 2.4 | 3.7 | 3.1 | 2.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Pavllo et al.Temporal modeling=Temporal2020.09 | 2.8 | 3 | 3.1 | 2.2 | 3.4 | 2.3 | 2.7 | 2.7 | 3.1 | 2.1 | 2.9 | 2.3 | 2.4 | 3.7 | 3.1 | 2.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Pavllo et al.Frames=243, 2D Detector=CPN2021.06 | 2.8 | 3 | 3.1 | 2.2 | 3.4 | 2.3 | 2.7 | 2.7 | 3.1 | 2.1 | 2.9 | 2.3 | 2.4 | 3.7 | 3.1 | 2.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VideoPose3DT=2432022.10 | 2.8 | 3 | 3.1 | 2.2 | 3.4 | 2.3 | 2.7 | 2.7 | 3.1 | 2.1 | 2.9 | 2.3 | 2.4 | 3.7 | 3.1 | 2.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerT=81, architecture=spatio-temporal Transformer2022.10 | 3.1 | 3.2 | 3.4 | 2.6 | 3.6 | 2.6 | 3 | 2.9 | 3.2 | 2.6 | 3.3 | 2.7 | 2.7 | 3.8 | 3.2 | 2.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UGCN2D Detector=CPN, Motion Loss=false2020.04 | 3.4 | 3.5 | 3.6 | 3 | 3.9 | 3 | 3.4 | 3.2 | 3.6 | 2.9 | 3.7 | 3 | 3.1 | 4.2 | 3.4 | 3.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Chen et al.Frames=9, 2D Detector=CPN2021.06 | 3.9 | 4.2 | 4.2 | 3.3 | 4.7 | 3.5 | 3.8 | 3.8 | 3.9 | 3.3 | 4 | 3.5 | 3.6 | 4.7 | 4.2 | 4.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Virtual BonesFrames=9, 2D Detector=CPN2021.06 | 3.9 | 4.2 | 4.2 | 3.3 | 4.7 | 3.5 | 3.8 | 3.8 | 3.9 | 3.2 | 3.9 | 3.5 | 3.6 | 4.8 | 4.3 | 4.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Pavllo et al.Temporal modeling=Single-frame2020.09 | 11.6 | 12.8 | 12.6 | 10.3 | 14.2 | 10.2 | 11.3 | 11.8 | 11.3 | 8.2 | 10.2 | 10.3 | 11.3 | 13.1 | 13.4 | 12.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TCPFormerT (Number of input frames)=243, Input type=Ground Truth 2D pose2025.01 | 15.5 | 15 | 15.9 | 16.1 | 14.2 | 15.7 | 16.4 | 16.2 | 16.9 | 22.1 | 20.6 | 16.7 | 13.3 | 13.8 | 9.2 | 9.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MotionBERTT=243, input=GT 2D, mode=finetune, architecture=spatio-temporal Transformer2022.10 | 16.9 | 15.9 | 17.3 | 16.9 | 14.6 | 16.8 | 18.6 | 18.6 | 18.4 | 22 | 21.8 | 17.3 | 16.9 | 16.1 | 10.5 | 11.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MotionBERTT=243, input=GT 2D, mode=scratch, architecture=spatio-temporal Transformer2022.10 | 17.8 | 16.7 | 19.9 | 17.1 | 16.5 | 17.4 | 18.8 | 19.3 | 20.5 | 24 | 22.1 | 18.6 | 16.8 | 16.7 | 10.8 | 11.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MotionBERTT (Number of input frames)=243, Input type=Ground Truth 2D pose2025.01 | 17.8 | 16.7 | 19.9 | 17.1 | 16.5 | 17.4 | 18.8 | 19.3 | 20.5 | 24 | 22.1 | 18.6 | 16.8 | 16.7 | 10.8 | 11.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D3DPN=243, H=20, K=10, Strategy=J-Best, Real-world feasibility=Not feasible, Category=Probabilistic, Input=Ground Truth 2D keypoints2023.03 | 18.4 | 18.7 | 18.2 | 18.4 | 17.8 | 18.6 | 20.9 | 20.2 | 17.7 | 23.8 | 21.8 | 18.5 | 17.4 | 17.4 | 13.1 | 13.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| KTPFormerT (Number of input frames)=243, Input type=Ground Truth 2D pose2025.01 | 19 | 19.6 | 18.6 | 18.5 | 18.1 | 18.7 | 22.1 | 20.8 | 18.3 | 22.8 | 22.4 | 18.8 | 18.1 | 18.4 | 13.9 | 15.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D3DPN=243, H=20, K=10, Strategy=P-Best, Real-world feasibility=Not feasible, Category=Probabilistic, Input=Ground Truth 2D keypoints2023.03 | 19.4 | 19.7 | 19.3 | 19.2 | 18.8 | 19.6 | 21.9 | 21.2 | 18.6 | 24.7 | 23 | 19.4 | 18.4 | 18.4 | 13.9 | 14.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DenseWarperInput Type=Sparse, 2D Pose Detector=SimpleBaseline2026.05 | 19.4 | 20.3 | 22.9 | 17.8 | 18.2 | 17.9 | 19 | 15.6 | 17.4 | 21.3 | 27.3 | 18.9 | 18.2 | — | 19 | 16.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D3DPN=243, H=20, K=10, Strategy=J-Agg, Category=Probabilistic, Input=Ground Truth 2D keypoints2023.03 | 19.6 | 19.9 | 19.4 | 19.4 | 19 | 19.8 | 22 | 21.4 | 19.1 | 24.8 | 23.2 | 19.6 | 18.7 | 18.6 | 14 | 14.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D3DPN=243, H=20, K=10, Strategy=P-Agg, Category=Probabilistic, Input=Ground Truth 2D keypoints2023.03 | 19.8 | 19.9 | 19.5 | 19.6 | 19.2 | 20.1 | 22.4 | 21.5 | 19.1 | 25.4 | 23.7 | 20 | 18.9 | 18.8 | 14 | 14.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D3DPN=243, H=1, K=1, Category=Deterministic, Input=Ground Truth 2D keypoints2023.03 | 19.9 | 19.9 | 19.6 | 19.7 | 19.3 | 20.2 | 22.7 | 21.5 | 19.2 | 25.5 | 24 | 20.1 | 18.9 | 19 | 14 | 14.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D3DPN=243, H=1, K=1, Strategy=P-Agg, Category=Probabilistic, Input=Ground Truth 2D keypoints2023.03 | 19.9 | 19.9 | 19.6 | 19.7 | 19.3 | 20.2 | 22.7 | 21.5 | 19.2 | 25.5 | 24 | 20.1 | 18.9 | 19 | 14 | 14.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D3DPN=243, H=1, K=1, Strategy=P-Best, Real-world feasibility=Not feasible, Category=Probabilistic, Input=Ground Truth 2D keypoints2023.03 | 19.9 | 19.9 | 19.6 | 19.7 | 19.3 | 20.2 | 22.7 | 21.5 | 19.2 | 25.5 | 24 | 20.1 | 18.9 | 19 | 14 | 14.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SgraformerInput Type=Multi-view full-frame, 2D Pose Detector=SimpleBaseline2026.05 | 19.9 | 19.9 | 20.1 | 18.1 | 18.2 | 20.8 | 20.3 | 17.1 | 17.7 | 23 | 26.2 | 21.9 | 18.6 | — | 17.7 | 17.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TCPFormerT (Number of input frames)=81, Input type=Ground Truth 2D pose2025.01 | 20.5 | 19.2 | 19.6 | 20.2 | 18.3 | 20.7 | 24 | 20.9 | 20.3 | 26.9 | 26.9 | 21.6 | 18.5 | 19.6 | 15.7 | 15.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AdafuseInput Type=Multi-view full-frame, 2D Pose Detector=SimpleBaseline2026.05 | 20.7 | 21 | 22.4 | 19.1 | 20.9 | 20.8 | 20.2 | 19.4 | 20 | 22.2 | 23.1 | 21.3 | 20.1 | — | 19.4 | 18.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Adafuse + MCCInput Type=Multi-view interpolated, Interpolation Method=MCC, 2D Pose Detector=SimpleBaseline2026.05 | 20.7 | 20.5 | 22.6 | 18.8 | 21 | 20.5 | 21 | 19.1 | 19.4 | 22.6 | 23.3 | 21.6 | 20.1 | — | 19.4 | 18.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Adafuse + SLERPInput Type=Multi-view interpolated, Interpolation Method=SLERP, 2D Pose Detector=SimpleBaseline2026.05 | 20.7 | 20.9 | 22.4 | 19 | 22.2 | 20.8 | 20.2 | 19.3 | 19.9 | 22.2 | 23 | 21.2 | 20.1 | — | 19.3 | 18.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLA-GCNT (Number of input frames)=243, Input type=Ground Truth 2D pose2025.01 | 21 | 20.1 | 21.2 | 20 | 19.6 | 21.5 | 26.7 | 23.3 | 19.8 | 27 | 29.4 | 20.8 | 20.1 | 19.2 | 12.8 | 13.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTEN=243, Category=Deterministic, Input=Ground Truth 2D keypoints, Implementation=Our implementation2023.03 | 21.3 | 22.9 | 21.7 | 21 | 21.4 | 20.8 | 23.5 | 24.1 | 21.8 | 25.3 | 23.5 | 21.4 | 20.1 | 19.5 | 15.3 | 16.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| STCFormerT (Number of input frames)=243, Input type=Ground Truth 2D pose2025.01 | 21.3 | 20.8 | 21.8 | 20 | 20.6 | 23.4 | 25 | 23.6 | 19.3 | 27.8 | 26.1 | 21.6 | 20.6 | 19.5 | 14.3 | 15.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTEinput=GT, T=2432022.03 | 21.6 | 21.6 | 22 | 20.4 | 21 | 20.8 | 24.3 | 24.7 | 21.9 | 26.9 | 24.9 | 21.2 | 21.5 | 20.8 | 14.7 | 15.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTEN=243, Category=Deterministic, Input=Ground Truth 2D keypoints2023.03 | 21.6 | 21.6 | 22 | 20.4 | 21 | 20.8 | 26.3 | 24.7 | 21.9 | 26.9 | 24.9 | 21.2 | 21.5 | 20.8 | 14.7 | 15.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTET=243, input=GT 2D, architecture=spatio-temporal Transformer2022.10 | 21.6 | 21.6 | 22 | 20.4 | 21 | 20.8 | 24.3 | 24.7 | 21.9 | 26.9 | 24.9 | 21.2 | 21.5 | 20.8 | 14.7 | 15.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTET (Number of input frames)=243, Input type=Ground Truth 2D pose2025.01 | 21.6 | 21.6 | 22 | 20.4 | 21 | 20.8 | 24.3 | 24.7 | 21.9 | 26.9 | 24.9 | 21.2 | 21.5 | 20.8 | 14.7 | 15.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AdafuseInput Type=Sparse, 2D Pose Detector=SimpleBaseline2026.05 | 21.7 | 22.5 | 22.6 | 19.7 | 22.5 | 21.5 | 20.9 | 20 | 20.5 | 22.5 | 23.4 | 21.7 | 20.6 | — | 23.3 | 20.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DUEN=300, Category=Deterministic, Input=Ground Truth 2D keypoints2023.03 | 22 | 22.1 | 23.1 | 20.1 | 22.7 | 21.3 | 24.1 | 23.6 | 21.6 | 26.3 | 24.8 | 21.7 | 21.4 | 21.8 | 16.7 | 18.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Wang et al.input=GT, T=962022.03 | 25.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UGCNT=96, input=GT 2D2022.10 | 25.6 | 23 | 25.7 | 22.8 | 22.6 | 24.1 | 30.6 | 24.9 | 24.5 | 31.1 | 35 | 25.6 | 24.3 | 25.1 | 19.8 | 18.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FinePoseInput Type=Single-view, 2D Pose Detector=SimpleBaseline, Time Frames (T)=2432026.05 | 25.6 | 24.8 | 26.3 | 24.7 | 24 | 27 | 28.1 | 22.4 | 23.8 | 33.7 | 33.3 | 27.4 | 24.6 | — | 19.2 | 18.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| KTPFormerFrames=T=243, Temporal info=true, Diffusion-based=true, Evaluation Protocol=P-MPJPE, 2D Detector=CPN2024.03 | 26.2 | 24.1 | 26.7 | 24.2 | 24.9 | 27.3 | 30.6 | 25.2 | 23.4 | 34.1 | 35.9 | 28.1 | 25.3 | 25.9 | 17.8 | 18.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Fusion-RPSMAlignment protocol=No Procrustes alignment, Additional training data=MPII2019.09 | 26.21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Epipolar transformersProtocol=Protocol 1, Coordinate Space=Absolute positions, Training Setup=No additional training data2021.10 | 26.9 | 25.7 | 27.7 | 23.7 | 24.8 | 26.9 | 31.4 | 24.9 | 26.5 | 28.8 | 31.7 | 28.2 | 26.4 | 23.6 | 28.3 | 23.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CrossFormerProtocol=Protocol 1, Input=Ground Truth 2D pose, f=812022.03 | 28.3 | 26 | 30 | 26.8 | 26.2 | 28 | 31 | 30.4 | 29.6 | 35.4 | 37.1 | 28.4 | 27.3 | 26.7 | 20.5 | 19.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| STEN=351, Category=Deterministic, Input=Ground Truth 2D keypoints2023.03 | 28.5 | 27.1 | 29.4 | 26.5 | 27.1 | 28.6 | 33 | 30.7 | 26.8 | 38.2 | 34.7 | 29.1 | 29.8 | 26.8 | 19.1 | 19.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D3DPPublication=ICCV’23, Frames=T=243, Temporal info=true, Diffusion-based=true, Evaluation Protocol=P-MPJPE, 2D Detector=CPN2024.03 | 28.7 | 27.5 | 29.4 | 26.6 | 27.7 | 29.2 | 34.3 | 27.5 | 26.2 | 37.3 | 39 | 30.3 | 27.7 | 28.2 | 19.6 | 20.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Ours (h_weight)Protocol=Protocol 1, Coordinate Space=Absolute positions, Training Setup=No additional training data2021.10 | 29.1 | 27.5 | 28.4 | 29.3 | 27.5 | 30.1 | 28.1 | 27.9 | 30.8 | 32.9 | 32.5 | 30.8 | 29.4 | 28.5 | 30.5 | 30.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| P-STMON=2432022.03 | 29.3 | 28.5 | 30.1 | 28.6 | 27.9 | 29.8 | 33.2 | 31.3 | 27.8 | 36 | 37.4 | 29.7 | 29.5 | 28.1 | 21 | 21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| P-STMON=243, Input=GT 2D poses2022.03 | 29.3 | 28.5 | 30.1 | 28.6 | 27.9 | 29.8 | 33.2 | 31.3 | 27.8 | 36 | 37.4 | 29.7 | 29.5 | 28.1 | 21 | 21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| P-STMON=243, Category=Deterministic, Input=Ground Truth 2D keypoints2023.03 | 29.3 | 28.5 | 30.1 | 28.6 | 27.9 | 29.8 | 33.2 | 31.3 | 27.8 | 36 | 37.4 | 29.7 | 29.5 | 28.1 | 21 | 21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| P-STMOT=243, input=GT 2D, architecture=spatio-temporal Transformer2022.10 | 29.3 | 28.5 | 30.1 | 28.6 | 27.9 | 29.8 | 33.2 | 31.3 | 27.8 | 36 | 37.4 | 29.7 | 29.5 | 28.1 | 21 | 21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| P-STMOT (Number of input frames)=243, Input type=Ground Truth 2D pose2025.01 | 29.3 | 28.5 | 30.1 | 28.6 | 27.9 | 29.8 | 33.2 | 31.3 | 27.8 | 36 | 37.4 | 29.7 | 29.5 | 28.1 | 21 | 21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseRNNumber of joints=42021.07 | 29.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SnapPose3DH=20, Selection Strategy=B, Input=CPN detections2026.04 | 29.7 | 30.8 | 29.2 | 29 | 27.8 | 28.2 | 31.6 | 30.6 | 33 | 32.1 | 33.3 | 29.6 | 27.2 | 28.3 | 27.9 | 24.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Shan et al.N=2432022.03 | 30.1 | 28.5 | 30.8 | 28.8 | 29.1 | 30.7 | 35.2 | 31.7 | 27.8 | 34.5 | 36 | 30.3 | 29.4 | 28.2 | 24.1 | 24.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Shan et al.N=243, Input=GT 2D poses2022.03 | 30.1 | 29.5 | 30.8 | 28.8 | 29.1 | 30.7 | 35.2 | 31.7 | 27.8 | 34.5 | 36 | 30.3 | 29.4 | 28.2 | 24.1 | 24.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RIEN=243, Category=Deterministic, Input=Ground Truth 2D keypoints2023.03 | 30.1 | 29.5 | 30.8 | 28.8 | 29.1 | 30.7 | 35.2 | 31.7 | 27.8 | 34.5 | 36 | 30.3 | 29.4 | 28.9 | 24.1 | 24.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Remelli et al.Protocol=Protocol 1, Coordinate Space=Absolute positions, Training Setup=No additional training data2021.10 | 30.2 | 27.3 | 32.1 | 25 | 26.5 | 29.3 | 35.4 | 28.8 | 31.6 | 36.4 | 31.7 | 31.2 | 29.9 | 26.9 | 33.7 | 30.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MHFormerN=351, H=3, Strategy=P-Agg, Category=Probabilistic, Input=Ground Truth 2D keypoints2023.03 | 30.5 | 27.7 | 32.1 | 29.1 | 28.9 | 30 | 33.9 | 33 | 31.2 | 37 | 39.3 | 30.3 | 31 | 29.4 | 22.2 | 23 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MHFormerT=351, input=GT 2D, architecture=spatio-temporal Transformer2022.10 | 30.5 | 27.7 | 32.1 | 29.1 | 28.9 | 30 | 33.9 | 33 | 31.2 | 37 | 39.3 | 30 | 31 | 29.4 | 22.2 | 23 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MHFormerT (Number of input frames)=351, Input type=Ground Truth 2D pose2025.01 | 30.5 | 27.7 | 32.1 | 29.1 | 28.9 | 30 | 33.9 | 33 | 31.2 | 37 | 39.3 | 30 | 31 | 29.4 | 22.2 | 23 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Sun et al.Protocol=Protocol 2, Setting=Paired, uses_soft_argmax=true2019.04 | 30.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTEdetector=HRNet, T=243, protocol=Protocol #22022.03 | 30.6 | 28 | 30.9 | 28.6 | 30.7 | 30.4 | 34.6 | 28.6 | 28.1 | 37.1 | 47.3 | 30.5 | 29.7 | 30.5 | 21.6 | 20 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| stochastic framework for human pose triangulationTrain Dataset=CMU Panoptic Studio, Train Camera Configuration=CMU32021.10 | 31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 8.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DiffPyramidparams=1.86M2025.06 | 31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseMoET=243, 2D Pose Detector=CPN2025.12 | 31 | 29.3 | 31.7 | 30.5 | 29 | 31.6 | 36.4 | 27.8 | 29.4 | 40 | 43.6 | 32.9 | 28.8 | 21.3 | 30.7 | 22.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Fusion-RPSMAlignment protocol=No Procrustes alignment, Additional training data=None2019.09 | 31.17 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DDHPoseProtocol=P-MPJPE, N=243, H=1, W=12024.03 | 31.2 | 29.5 | 31.9 | 28.7 | 30.1 | 31.3 | 35.5 | 29.7 | 29.5 | 41.8 | 42.9 | 33.4 | 29.7 | 30.4 | 21.7 | 22.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DDHPoseProtocol=P-MPJPE, Method category=Probabilistic, N=243, H=5, W=12024.03 | 31.2 | 29.5 | 31.8 | 28.7 | 30.1 | 31.3 | 35.6 | 29.7 | 29.5 | 41.7 | 42.9 | 33.4 | 29.6 | 30.4 | 21.7 | 22.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DDHPoseProtocol=P-MPJPE, Method category=Probabilistic, N=243, H=20, W=102024.03 | 31.2 | 29.4 | 32.1 | 28.4 | 30.1 | 31 | 35.3 | 29.5 | 29.2 | 41.7 | 42.7 | 33.2 | 29.7 | 30.6 | 21.5 | 22.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Cross-view fusionProtocol=Protocol 1, Coordinate Space=Absolute positions, Training Setup=No additional training data2021.10 | 31.2 | 28.9 | 32.5 | 26.6 | 28.1 | 28.3 | 29.3 | 28 | 36.8 | 41 | 30.5 | 35.6 | 30 | 28.3 | 30 | 30.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerProtocol=Protocol 1, Input=Ground Truth 2D pose, f=812022.03 | 31.3 | 30 | 33.6 | 29.9 | 31 | 30.2 | 33.3 | 34.8 | 31.4 | 37.8 | 38.6 | 31.7 | 31.5 | 29 | 23.3 | 23.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Zheng et al.N=812022.03 | 31.3 | 30 | 33.6 | 29.9 | 31 | 30.2 | 33.3 | 34.8 | 31.4 | 37.8 | 38.6 | 31.7 | 31.5 | 29 | 23.3 | 23.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Zheng et al.N=81, Input=GT 2D poses2022.03 | 31.3 | 30 | 33.6 | 29.9 | 31 | 30.2 | 33.3 | 34.8 | 31.4 | 37.8 | 38.6 | 31.7 | 31.5 | 29 | 23.3 | 23.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerN=81, Category=Deterministic, Input=Ground Truth 2D keypoints2023.03 | 31.3 | 30 | 33.6 | 29.9 | 31 | 30.2 | 33.3 | 34.8 | 31.4 | 37.8 | 38.6 | 31.7 | 31.5 | 29 | 23.3 | 23.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerT=81, input=GT 2D, architecture=spatio-temporal Transformer2022.10 | 31.3 | 30 | 33.6 | 29.9 | 31 | 30.2 | 33.3 | 34.8 | 31.4 | 37.8 | 38.6 | 31.7 | 31.5 | 29 | 23.3 | 23.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| KTP-FormerInput Type=Single-view, 2D Pose Detector=SimpleBaseline, Time Frames (T)=2432026.05 | 31.4 | 28.6 | 31.1 | 28.3 | 28.9 | 32.7 | 34.9 | 29 | 29.2 | 39.9 | 47.3 | 33.5 | 29 | — | 22.4 | 23.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D3DPProtocol=P-MPJPE, Method category=Probabilistic, N=243, H=20, W=102024.03 | 31.6 | 30.6 | 32.4 | 29.2 | 30.9 | 31.9 | 37.4 | 30.2 | 29.3 | 40.4 | 43.2 | 33.2 | 30.4 | 31.3 | 21.5 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| STCFormerProtocol=P-MPJPE, Method category=Deterministic: Non-Disentangle-based, N=2432024.03 | 31.8 | 29.3 | 33 | 30.7 | 30.6 | 32.7 | 38.2 | 29.7 | 28.8 | 42.2 | 45 | 33.3 | 29.4 | 31.5 | 20.9 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GraphMDNN=1, H=5, Strategy=P-Best, Real-world feasibility=Not feasible, Category=Probabilistic, Input=Ground Truth 2D keypoints2023.03 | 31.8 | 28.9 | 34.5 | 28.2 | 30.2 | 31.5 | 38.5 | 32.3 | 28.6 | 35.7 | 43.3 | 31.9 | 32.1 | 33.3 | 25.2 | 27.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| STCFormerPublication=CVPR’23, Frames=T=243, Temporal info=true, Diffusion-based=false, Evaluation Protocol=P-MPJPE, 2D Detector=CPN2024.03 | 31.8 | 29.3 | 33 | 30.7 | 30.6 | 32.7 | 38.2 | 29.7 | 28.8 | 42.2 | 45 | 33.3 | 29.4 | 31.5 | 20.9 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| STCFormerVenue=CVPR’23, T=243, 2D Pose Detector=CPN2025.12 | 31.8 | 29.3 | 33 | 30.7 | 30.6 | 32.7 | 38.2 | 29.7 | 28.8 | 42.2 | 45 | 33.3 | 29.4 | 31.5 | 20.9 | 22.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| KTPFormerFrames=T=243, Temporal info=true, Diffusion-based=false, Evaluation Protocol=P-MPJPE, 2D Detector=CPN2024.03 | 31.9 | 30.1 | 32.3 | 29.6 | 30.8 | 32.3 | 37.3 | 30 | 30.2 | 41 | 45.3 | 33.6 | 29.9 | 31.4 | 21.5 | 22.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| KTPFormerVenue=CVPR’24, T=243, 2D Pose Detector=CPN2025.12 | 31.9 | 30.1 | 32.3 | 29.6 | 30.8 | 32.3 | 37.3 | 30 | 30.2 | 41 | 45.3 | 33.6 | 29.9 | 31.4 | 21.5 | 22.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SRNetProtocol=Protocol 1, Input=Ground Truth 2D pose2022.03 | 32 | 34.8 | 32.1 | 28.5 | 30.7 | 31.4 | 36.9 | 35.6 | 30.5 | 38.9 | 40.5 | 32.5 | 31 | 29.9 | 22.5 | 24.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Zeng et al.N=2432022.03 | 32 | 34.8 | 32.1 | 28.5 | 30.7 | 31.4 | 36.9 | 35.6 | 30.5 | 38.9 | 40.5 | 32.5 | 31 | 29.9 | 22.5 | 24.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Zeng et al.N=243, Input=GT 2D poses2022.03 | 32 | 34.8 | 32.1 | 28.5 | 30.7 | 31.4 | 36.9 | 35.6 | 30.5 | 38.9 | 40.5 | 32.5 | 31 | 29.9 | 22.5 | 24.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SRNetN=243, Category=Deterministic, Input=Ground Truth 2D keypoints2023.03 | 32 | 34.8 | 32.1 | 28.5 | 30.7 | 31.4 | 36.9 | 35.6 | 30.5 | 38.9 | 40.5 | 32.5 | 31 | 29.9 | 22.5 | 24.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DiffPoseH=200, Selection Strategy=B, Input=CPN detections2026.04 | 32 | 28.1 | 31.5 | 28 | 30.8 | 33.6 | 35.3 | 28.5 | 27.6 | 40.8 | 44.6 | 31.8 | 32.1 | 32.6 | 28.1 | 26.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Chen et al.Protocol=Protocol 1, Input=Ground Truth 2D pose, f=2432022.03 | 32.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |