3D Human Pose Estimation on Human3.6M standard (test)
34.4Avg MPJPE ErrorP-STMO
Evaluation Results
| Method | Links | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| P-STMON=243, 2D Detector=CPN2022.03 | 34.4 | 31.3 | 35.2 | 32.9 | 33.9 | 35.4 | 39.3 | 32.5 | 31.5 | 44.6 | 48.2 | 36.3 | 32.9 | 34.4 | 23.8 | 23.9 | — | — | |
| Zheng et al.N=81, 2D Detector=CPN2022.03 | 34.6 | 32.5 | 34.8 | 32.6 | 34.6 | 35.3 | 39.5 | 32.1 | 32 | 42.8 | 48.5 | 34.8 | 32.4 | 35.3 | 24.5 | 26 | — | — | |
| Shan et al.N=243, 2D Detector=CPN2022.03 | 35 | 32.5 | 36.2 | 33.2 | 35.3 | 35.6 | 42.1 | 32.6 | 31.9 | 42.6 | 47.9 | 36.6 | 32.1 | 34.8 | 24.2 | 25.8 | — | — | |
| Wang et al.N=96, 2D Detector=CPN2022.03 | 35.5 | 32.9 | 35.2 | 35.6 | 34.4 | 36.4 | 42.7 | 31.2 | 32.5 | 45.6 | 50.2 | 37.3 | 32.8 | 36.3 | 26 | 23.9 | — | — | |
| Liu et al.N=243, 2D Detector=CPN2022.03 | 35.6 | 32.3 | 35.2 | 33.3 | 35.8 | 35.9 | 41.5 | 33.2 | 32.7 | 44.6 | 50.9 | 37 | 32.4 | 37 | 25.2 | 27.2 | — | — | |
| Chen et al.N=243, 2D Detector=CPN2022.03 | 35.6 | 33.1 | 35.3 | 33.4 | 35.9 | 36.1 | 41.7 | 32.8 | 33.3 | 42.6 | 49.4 | 37 | 32.7 | 36.5 | 25.5 | 27.9 | — | — | |
| Xu et al.N=9, 2D Detector=CPN2022.03 | 36.2 | 31 | 34.8 | 34.7 | 34.4 | 36.2 | 43.9 | 31.6 | 33.5 | 42.3 | 49 | 37.1 | 33 | 39.1 | 26.9 | 31.9 | — | — | |
| Pavllo et al.N=243, 2D Detector=CPN2022.03 | 36.5 | 34.1 | 36.1 | 34.4 | 37.2 | 36.4 | 42.2 | 34.4 | 33.6 | 45 | 52.5 | 37.4 | 33.8 | 37.8 | 25.6 | 27.3 | — | — | |
| Lin et al.N=50, 2D Detector=CPN2022.03 | 36.8 | 32.5 | 35.3 | 34.3 | 36.2 | 37.8 | 43 | 33 | 32.2 | 45.7 | 51.8 | 38.4 | 32.8 | 37.5 | 25.8 | 28.9 | — | — | |
| MASC-PoseVenue=-, CE=✗, T=243, Parameter=13.0M, MACs=53.4G, MACs/frames=219M2026.04 | 37.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.8 | 16 | |
| TCPFormerVenue=AAAI’25, CE=✗, T=243, Parameter=35.1M, MACs=109.2G, MACs/frames=449M2026.04 | 37.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.7 | 15.5 | |
| MotionAGFormer-LVenue=CVPR’24, CE=✗, T=243, Parameter=19.0M, MACs=78.3G, MACs/frames=322M2026.04 | 38.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.5 | 17.3 | |
| H2OT + MotionAGFormerVenue=TPAMI’25, CE=✗, T=243, Parameter=11.7M, MACs=38.9G2026.04 | 38.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HGMamba-BVenue=IJCNN’25, CE=✗, T=243, Parameter=14.2M, MACs=64.5G, MACs/frames=265M2026.04 | 38.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.9 | 13.2 | |
| MotionBERTVenue=ICCV’23, CE=✗, T=243, Parameter=42.3M, MACs=174.8G, MACs/frames=719M2026.04 | 39.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.9 | 17.8 | |
| KTPFormerVenue=CVPR’24, CE=✗, T=243, Parameter=33.7M, MACs=69.5G, MACs/frames=286M2026.04 | 40.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.9 | 19 | |
| MixSTEVenue=CVPR’22, CE=✗, T=243, Parameter=33.6M, MACs=139.0G, MACs/frames=572M2026.04 | 40.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.6 | 21.6 | |
| P-STMOVenue=ECCV’22, CE=✓, T=243, Parameter=6.2M, MACs=0.7G, MACs/frames=740M2026.04 | 42.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.4 | 29.3 | |
| GLA-GCNVenue=ICCV’23, CE=✓, T=243, Parameter=1.3M, MACs=1.5G, MACs/frames=1556M2026.04 | 44.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.8 | 21 | |
| PoseFormerV2f=27, Seq. Len.=243, MFLOPS=1054.82023.03 | 45.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 35.6 | — | |
| PoseFormerV2Venue=CVPR’23, CE=✓, T=243, Parameter=14.3M, MACs=0.5G, MACs/frames=528M2026.04 | 45.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 35.6 | — | |
| P-STMOf=81, Seq. Len.=81, MFLOPS=493, additional_pre-training=true2023.03 | 45.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MHFormerf=27, Seq. Len.=27, MFLOPS=1031.82023.03 | 45.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerV2f=9, Seq. Len.=81, MFLOPS=351.72023.03 | 46 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 36.1 | — | |
| P-STMOf=27, Seq. Len.=81, MFLOPS=163, additional_pre-training=true2023.03 | 46.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerV1f=27, Seq. Len.=27, MFLOPS=542.12023.03 | 47 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerV2f=3, Seq. Len.=81, MFLOPS=117.32023.03 | 47.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 37.3 | — | |
| StridedTransformerf=81, Seq. Len.=81, MFLOPS=342.52023.03 | 47.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerV2f=1, Seq. Len.=81, MFLOPS=77.22023.03 | 47.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 37.3 | — | |
| PoseFormerV2f=9, Seq. Len.=27, MFLOPS=351.72023.03 | 47.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 37.1 | — | |
| MHFormerf=9, Seq. Len.=9, MFLOPS=342.92023.03 | 47.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Einfalt et al.f=9, Seq. Len.=81, MFLOPS=5432023.03 | 47.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| PoseFormerV2f=3, Seq. Len.=27, MFLOPS=117.32023.03 | 47.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 37.4 | — | |
| PoseFormerV2f=1, Seq. Len.=27, MFLOPS=77.22023.03 | 48.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 37.8 | — | |
| PoseFormerV2f=3, Seq. Len.=9, MFLOPS=117.32023.03 | 49.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 38.5 | — | |
| MixSTEf=3, Seq. Len.=3, MFLOPS=3420, implementation=re-implementation2023.03 | 49.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 38.9 | — | |
| PoseFormerV2f=1, Seq. Len.=9, MFLOPS=77.22023.03 | 49.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 38.7 | — |