3D Human Pose Estimation on Human3.6M
16.5MPJPEPoseMoE
Evaluation Results
| Method | Links | ||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PoseMoENetwork=Mixture-of-Experts, Seq2Seq=true, T=243, Parameter=17.9M, MACs=66.3G, MACs/frame=272M2025.12 | 16.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Volumetric2D pose detector fine-tuned=true2023.12 | 17.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| KTPFormerVenue=CVPR’24, Network=Lifting-Based, Seq2Seq=true, T=243, Parameter=33.7M, MACs=69.5G, MACs/frame=286M2025.12 | 19 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Algebraic Triangulation2D pose detector fine-tuned=true2023.12 | 19.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLA-GCNVenue=ICCV’23, Network=Lifting-Based, Seq2Seq=false, T=243, Parameter=1.3M, MACs=1.5G, MACs/frame=1556M2025.12 | 21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| STCFormerVenue=CVPR’23, Network=Lifting-Based, Seq2Seq=true, T=243, Parameter=4.7M, MACs=19.6G, MACs/frame=80M2025.12 | 21.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseRetNetVenue=ECCV’24, Network=Lifting-Based, Seq2Seq=true, T=243, Parameter=25.2M, MACs=104.5G, MACs/frame=430M2025.12 | 21.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTEVenue=CVPR’22, Network=Lifting-Based, Seq2Seq=true, T=243, Parameter=33.6M, MACs=139.0G, MACs/frame=572M2025.12 | 21.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Geometry-Biased TransformerBackbone=ResNet-152, 2D pose detector fine-tuned=true2023.12 | 22.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TransFusion2D pose detector fine-tuned=true2023.12 | 25.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Geometry-Biased TransformerBackbone=HRNet, 2D pose detector fine-tuned=false2023.12 | 26 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Cross View Fusion2D pose detector fine-tuned=true2023.12 | 26.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Epipolar Transformers2D pose detector fine-tuned=true2023.12 | 27.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HeatFormerOptimization iterations=iter3, Translation estimation protocol=ground-truth 3D joints2024.12 | 28.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| P-STMOVenue=ECCV’22, Network=Lifting-Based, Seq2Seq=false, T=243, Parameter=6.2M, MACs=0.7G, MACs/frame=740M2025.12 | 29.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HeatFormerOptimization iterations=iter42024.12 | 29.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 22.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HTP (Ours)Type=Diffusion, F=243, CE=false, Detector=CPN, MACs (G)=87.7, Params (M)=37.52025.08 | 29.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.3 | — | — | — | — | — | — | — | |
| Remelli et al.2D pose detector fine-tuned=true2023.12 | 30.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GraphMLPInput Source=GT, Sequence length (T)=2432022.06 | 30.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MHFormerVenue=CVPR’22, Network=Lifting-Based, Seq2Seq=false, T=351, Parameter=30.9M, MACs=7.1G, MACs/frame=7096M2025.12 | 30.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HeatFormerOptimization iterations=iter32024.12 | 30.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| U-HMR2024.12 | 31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 22.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerInput Source=GT, Sequence length (T)=812022.06 | 31.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FinePOSEType=Diffusion, Publication=CVPR’24, F=243, CE=false, Detector=CPN, MACs (G)=146, Params (M)=200.62025.08 | 31.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 25 | — | — | — | — | — | — | — | |
| SRNetInput Source=GT, Sequence length (T)=2432022.06 | 32 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Anatomy3DInput Source=GT, Sequence length (T)=2432022.06 | 32.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PaFF2024.12 | 33 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 26.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| KTPFormerType=Diffusion, Publication=CVPR’24, F=243, CE=false, Detector=CPN, MACs (G)=139.1, Params (M)=36.32025.08 | 33 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 26.2 | — | — | — | — | — | — | — | |
| BaselineInput Source=GT, Sequence length (T)=2432022.06 | 35.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| D3DPType=Diffusion, Publication=ICCV’23, F=243, CE=false, Detector=CPN, MACs (G)=139.1, Params (M)=34.82025.08 | 35.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 28.7 | — | — | — | — | — | — | — | |
| HYPERPOSEGeometry=H^d, Temporal Receptive Field (T)=243, 2D Keypoints=CPN2026.05 | 36 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 29.11 | — | — | — | — | — | — | 35.08 | |
| MeTRAbs-ACAE-Lvariant=L2024.07 | 36.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 27.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MambaposeTemplate-based=false, Kinematics-based=false, Online=false2026.01 | 36.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 28.6 | — | — | — | — | — | — | — | |
| DiffPoseAcceleration strategy=w/o DDIM2022.11 | 36.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 173 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DiffPoseAcceleration strategy=w/ DDIM2022.11 | 36.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 671 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SAMA-LType=Mamba, Publication=ICCV’25, F=243, CE=false, Detector=CPN, MACs (G)=53.2, Params (M)=17.32025.08 | 36.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.3 | — | — | — | — | — | — | — | |
| DiffposeType=Diffusion, Publication=CVPR’23, F=243, CE=false, Detector=CPN2025.08 | 36.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 28.7 | — | — | — | — | — | — | — | |
| PoseMambaTemplate-based=false, Kinematics-based=false, Online=false2026.01 | 37.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.5 | — | — | — | — | — | — | — | |
| PoseMamba-XType=Mamba, Publication=AAAI’25, F=243, CE=false, Detector=CPN, MACs (G)=109.9, Params (M)=26.52025.08 | 37.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.5 | — | — | — | — | — | — | — | |
| ST-GCNInput Source=GT, Sequence length (T)=92022.06 | 37.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MotionBERTType=Transformer, Publication=ICCV’23, F=243, CE=false, Detector=SH, Setting=Finetune Setting, MACs (G)=174.8, Params (M)=42.52025.08 | 37.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TCNInput Source=GT, Sequence length (T)=2432022.06 | 37.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TCPFormerSeq2Seq=true, Number of input frames=243, Parameter=35.1M, MACs=109.2G, MACs/frames=449M2025.01 | 37.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MotionAGFormerGeometry=Euc., Temporal Receptive Field (T)=243, 2D Keypoints=CPN2026.05 | 38.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.4 | — | — | — | — | — | — | 38.16 | |
| HTP w/ MotionBERTType=Transformer, F=243, CE=false, Detector=SH, Setting=Scratch Setting, MACs (G)=101.7, Params (M)=47.62025.08 | 38.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MotionBERTSeq2Seq=true, Number of input frames=243, Parameter=42.3M, MACs=174.8G, MACs/frames=719M2025.01 | 39.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MotionBERTType=Transformer, Publication=ICCV’23, F=243, CE=false, Detector=SH, Setting=Scratch Setting, MACs (G)=174.8, Params (M)=42.52025.08 | 39.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MotionBERTGeometry=Euc., Temporal Receptive Field (T)=243, 2D Keypoints=CPN2026.05 | 39.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.9 | — | — | — | — | — | — | 39 | |
| NLF-Lvariant=L2024.07 | 39.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 28.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CA-PF-HRNet-482D Pose Detector=HRNet-48 [53], Frame=1, FLOPs (G) for the Lifting Module=0.62023.11 | 39.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TC-MixSTEType=Transformer, Publication=TMM’24, F=243, CE=false, Detector=CPN2025.08 | 39.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.9 | — | — | — | — | — | — | — | |
| HTP w/ MixSTEType=Transformer, F=243, CE=false, Detector=CPN, MACs (G)=87.6, Params (M)=36.42025.08 | 39.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 29.9 | — | — | — | — | — | — | — | |
| KTPFormerSeq2Seq=true, Number of input frames=243, Parameter=33.7M, MACs=69.5G, MACs/frames=286M2025.01 | 40.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| KTPFormerTemplate-based=false, Kinematics-based=false, Online=false2026.01 | 40.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.9 | — | — | — | — | — | — | — | |
| MeTRAbs-ACAE-Svariant=S2024.07 | 40.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseAnchorTemplate-based=false, Kinematics-based=false, Online=false2026.01 | 40.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.1 | — | — | — | — | — | — | — | |
| NLF-Svariant=S2024.07 | 40.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TCPFormerSeq2Seq=true, Number of input frames=81, Parameter=35.0M, MACs=36.4G, MACs/frames=150M2025.01 | 40.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 33.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| STCFormerType=Transformer, Publication=CVPR’23, F=243, CE=false, Detector=CPN, MACs (G)=78.2, Params (M)=18.92025.08 | 40.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.8 | — | — | — | — | — | — | — | |
| STCFormerGeometry=Euc., Temporal Receptive Field (T)=243, 2D Keypoints=CPN2026.05 | 40.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.8 | — | — | — | — | — | — | — | |
| Zhang2022.11 | 40.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 974 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTEVenue=CVPR'22, 2D Pose Detector=CPN [8], Frame=243, FLOPs (G) for the Lifting Module=277.42023.11 | 40.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTESeq2Seq=true, Number of input frames=243, Parameter=33.6M, MACs=139.0G, MACs/frames=572M2025.01 | 40.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MixSTEType=Transformer, Publication=CVPR’22, F=243, CE=false, Detector=CPN, MACs (G)=139.0, Params (M)=33.82025.08 | 40.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.6 | — | — | — | — | — | — | — | |
| MixSTEGeometry=Euc., Temporal Receptive Field (T)=243, 2D Keypoints=CPN2026.05 | 40.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.6 | — | — | — | — | — | — | — | |
| STCFormerSeq2Seq=true, Number of input frames=243, Parameter=4.7M, MACs=19.6G, MACs/frames=80M2025.01 | 41 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HOTType=Transformer, Publication=CVPR’24, F=243, CE=false, Detector=CPN, MACs (G)=83.8, Params (M)=35.02025.08 | 41 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CA-PF-HRNet-322D Pose Detector=HRNet-32 [53], Frame=1, FLOPs (G) for the Lifting Module=0.62023.11 | 41.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 33.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CA-PF-CPN2D Pose Detector=CPN [8], Frame=1, FLOPs (G) for the Lifting Module=0.62023.11 | 41.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 33.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Tang et al.Temporal Information=true, 2D Keypoint Input=CPN detections, Pose Refinement=false2025.06 | 42 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 40.6 | 43 | 38.3 | 40.2 | 43.5 | 52.6 | 40.3 | 40.1 | 51.8 | 57.7 | 42.8 | 39.8 | 42.3 | 28 | 29.5 | — | — | — | — | — | — | — | — | |
| Zhou et al.Temporal Information=true, 2D Keypoint Input=CPN detections, Pose Refinement=false2025.06 | 42 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 40.2 | 42.7 | 38.6 | 40.8 | 42.6 | 50 | 40.3 | 40.2 | 52.5 | 55.1 | 43.6 | 41.3 | 42.9 | 29.5 | 29.5 | — | — | — | — | — | — | — | — | |
| ProHMROutput type=Minimum error of distribution2021.08 | 42.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Li and LeeOutput type=Minimum error of distribution2021.08 | 42.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| P-STMOSeq2Seq=false, Number of input frames=243, Parameter=6.2M, MACs=0.7G, MACs/frames=740M2025.01 | 42.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| P-STMOType=Transformer, Publication=ECCV’22, F=243, CE=true, Detector=CPN, MACs (G)=1.7, Params (M)=7.02025.08 | 42.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.4 | — | — | — | — | — | — | — | |
| DualFormerType=Transformer, Publication=TCSVT’24, F=351, CE=false, Detector=CPN2025.08 | 42.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.4 | — | — | — | — | — | — | — | |
| DiffposeType=Diffusion, Publication=ICCV’23, F=64, CE=false2025.08 | 42.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.8 | — | — | — | — | — | — | — | |
| Li2022.11 | 43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 328 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MHFormerVenue=CVPR'22, 2D Pose Detector=CPN [8], Frame=351, FLOPs (G) for the Lifting Module=14.22023.11 | 43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| P-STMOVenue=ECCV'22, 2D Pose Detector=CPN [8], Frame=243, FLOPs (G) for the Lifting Module=1.52023.11 | 43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MHFormerSeq2Seq=false, Number of input frames=351, Parameter=30.9M, MACs=7.1G, MACs/frames=7096M2025.01 | 43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Li et al.Temporal Information=true, 2D Keypoint Input=CPN detections, Pose Refinement=false2025.06 | 43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 39.2 | 43.1 | 40.1 | 40.9 | 44.9 | 51.2 | 40.6 | 41.3 | 53.5 | 60.3 | 43.7 | 41.1 | 43.8 | 29.8 | 30.6 | — | — | — | — | — | — | — | — | |
| MHFormerType=Transformer, Publication=CVPR’22, F=351, CE=true, Detector=CPN, MACs (G)=9.6, Params (M)=24.72025.08 | 43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.4 | — | — | — | — | — | — | — | |
| MHFormerGeometry=Euc., Temporal Receptive Field (T)=351, 2D Keypoints=CPN2026.05 | 43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StridedTrans.Venue=TMM'22, 2D Pose Detector=CPN [8], Frame=351, FLOPs (G) for the Lifting Module=2.12023.11 | 43.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 35.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Li et al.Temporal Information=true, 2D Keypoint Input=CPN detections, Pose Refinement=false, Source=TMM'222025.06 | 43.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 40.3 | 43.3 | 40.2 | 42.3 | 45.6 | 52.3 | 41.8 | 40.5 | 55.9 | 60.6 | 44.2 | 43 | 44.2 | 30 | 30.2 | — | — | — | — | — | — | — | — | |
| CLIFF + PROMorthogonalization=PROM2023.12 | 43.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GraphMLPInput Source=CPN, Sequence length (T)=2432022.06 | 43.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SemGCNGeometry=Euc., Temporal Receptive Field (T)=1, 2D Keypoints=CPN2026.05 | 43.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Anatomy3DInput Source=CPN, Sequence length (T)=2432022.06 | 44.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Algebraic TriangulationBackbone=HRNet, 2D pose detector fine-tuned=false2023.12 | 44.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerVenue=ICCV'21, 2D Pose Detector=CPN [8], Frame=81, FLOPs (G) for the Lifting Module=1.42023.11 | 44.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerInput Source=CPN, Sequence length (T)=812022.06 | 44.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Zheng et al.Temporal Information=true, 2D Keypoint Input=CPN detections, Pose Refinement=false2025.06 | 44.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 41.5 | 44.8 | 39.8 | 42.5 | 46.5 | 51.6 | 42.1 | 42 | 53.3 | 60.7 | 45.5 | 43.3 | 46.1 | 31.8 | 32.2 | — | — | — | — | — | — | — | — | |
| PoseFormerType=Transformer, Publication=ICCV’21, F=81, CE=true, Detector=CPN, MACs (G)=1.6, Params (M)=9.62025.08 | 44.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 36.5 | — | — | — | — | — | — | — | |
| PoseFormerGeometry=Euc., Temporal Receptive Field (T)=81, 2D Keypoints=CPN2026.05 | 44.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.6 | — | — | — | — | — | — | — | |
| GLA-GCNSeq2Seq=false, Number of input frames=243, Parameter=1.3M, MACs=1.5G, MACs/frames=1556M2025.01 | 44.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLA-GCNType=GCN, Publication=ICCV’23, F=243, CE=true, Detector=CPN2025.08 | 44.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.8 | — | — | — | — | — | — | — | |
| PostureHMR2024.12 | 44.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Wang et al.Temporal Information=true, 2D Keypoint Input=CPN detections, Pose Refinement=false2025.06 | 44.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 40.2 | 42.5 | 42.6 | 41.1 | 46.7 | 56.7 | 41.4 | 42.3 | 56.2 | 60.4 | 46.3 | 42.2 | 46.2 | 31.7 | 31 | — | — | — | — | — | — | — | — |