Whole-body pose estimation on COCO-WholeBody 1.0 2017 (val)
67.5Whole-body APCIGPose-x + UBody
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| CIGPose-x + UBodyInput Size=384×288, GFLOPs=18.7, Estimation Approach=Top-down, Additional training data (UBody)=true, Flip test=true2026.03 | 67.5 | 75.5 | 73.5 | 80.1 | 70.3 | 81.6 | 88.4 | 92.7 | 62.6 | 72.6 | |
| CIGPose-xInput Size=384×288, GFLOPs=18.7, Estimation Approach=Top-down, Flip test=true2026.03 | 67 | 75.4 | 73.5 | 80.3 | 72.3 | 83.5 | 88.1 | 92.4 | 60.2 | 71 | |
| CIGPose-l + UBodyInput Size=384×288, GFLOPs=10.7, Estimation Approach=Top-down, Additional training data (UBody)=true, Flip test=true2026.03 | 66.9 | 75.1 | 73.1 | 79.6 | 72.3 | 82.7 | 88 | 92.5 | 61.2 | 71.6 | |
| DWPose-lInput Size=384×288, GFLOPs=10.1, Estimation Approach=Top-down, Two-stage distillation=true, Additional training data (UBody)=true, Flip test=true2026.03 | 66.5 | 74.3 | 72.2 | 78.9 | 70.4 | 81.7 | 88.7 | 92.1 | 62.1 | 71 | |
| CIGPose-lInput Size=384×288, GFLOPs=10.7, Estimation Approach=Top-down, Flip test=true2026.03 | 66.3 | 74.9 | 73 | 79.9 | 72 | 83.3 | 88.3 | 92.3 | 59.8 | 70 | |
| ZoomNASInput Size=384×288, GFLOPs=18.0, Estimation Approach=Top-down, Flip test=true2026.03 | 65.4 | 74.4 | 74 | 80.7 | 61.7 | 71.8 | 88.9 | 93 | 62.5 | 74 | |
| RTMPose-l + UBodyInput Size=384×288, GFLOPs=10.1, Estimation Approach=Top-down, Additional training data (UBody)=true, Flip test=true2026.03 | 65.4 | 73.2 | 71 | 77.9 | 68.6 | 80.2 | 88.5 | 92.2 | 60.6 | 69.9 | |
| RTMPose-xInput Size=384×288, GFLOPs=18.1, Estimation Approach=Top-down, Flip test=true2026.03 | 65.3 | 73.3 | 71.4 | 78.4 | 69.2 | 81 | 88.9 | 92.3 | 59 | 68.5 | |
| RTMPose-lInput Size=384×288, GFLOPs=10.1, Estimation Approach=Top-down, Flip test=true2026.03 | 64.8 | 73 | 71.2 | 78.1 | 69.3 | 81.1 | 88.2 | 91.9 | 57.9 | 67.7 | |
| DWPose-lInput Size=256×192, GFLOPs=4.5, Estimation Approach=Top-down, Two-stage distillation=true, Additional training data (UBody)=true, Flip test=true2026.03 | 63.1 | 71.7 | 70.4 | 77.7 | 66.2 | 79 | 84.3 | 89.4 | 56.6 | 66.5 | |
| ZoomNetInput Size=384×288, GFLOPs=28.5, Estimation Approach=Top-down, Flip test=true2026.03 | 63 | 74.2 | 74.5 | 81 | 60.9 | 70.8 | 88 | 92.4 | 57.9 | 73.4 | |
| CIGPose-lInput Size=256×192, GFLOPs=4.6, Estimation Approach=Top-down, Flip test=true2026.03 | 62.6 | 71.9 | 71.2 | 78.5 | 69 | 80.8 | 83.3 | 89.1 | 54 | 64.9 | |
| RTMPose-l + UBodyInput Size=256×192, GFLOPs=4.5, Estimation Approach=Top-down, Additional training data (UBody)=true, Flip test=true2026.03 | 62.1 | 70.6 | 69.7 | 76.9 | 65.5 | 78.1 | 84.1 | 89.3 | 55.1 | 65.4 | |
| ViTPose+-HInput Size=256×192, GFLOPs=122.9, Estimation Approach=Top-down, Flip test=true2026.03 | 61.2 | — | 75.9 | — | 77.9 | — | 63.3 | — | 54.7 | — | |
| RTMPose-lInput Size=256×192, GFLOPs=4.5, Estimation Approach=Top-down, Flip test=true2026.03 | 61.1 | 70 | 69.5 | 76.9 | 65.8 | 78.5 | 83.3 | 88.7 | 51.9 | 62.8 | |
| DWPose-mInput Size=256×192, GFLOPs=2.2, Estimation Approach=Top-down, Two-stage distillation=true, Additional training data (UBody)=true, Flip test=true2026.03 | 60.6 | 69.5 | 68.5 | 76.1 | 63.6 | 77.2 | 82.8 | 88.1 | 52.7 | 63.4 | |
| CIGPose-mInput Size=256×192, GFLOPs=2.3, Estimation Approach=Top-down, Flip test=true2026.03 | 59.9 | 69.4 | 69 | 76.6 | 64.3 | 77.6 | 82.1 | 88.3 | 49.7 | 61.6 | |
| FastPose50-dcn-siInput Size=256×192, GFLOPs=6.1, Estimation Approach=Top-down, Flip test=true2026.03 | 59.2 | 66.5 | 70.6 | 75.6 | 70.2 | 77.5 | 77.5 | 82.5 | 45.7 | 53.9 | |
| PVTInput Size=384×288, GFLOPs=19.7, Estimation Approach=Top-down, Flip test=true2026.03 | 58.9 | 68.9 | 67.3 | 76.1 | 66 | 79.4 | 74.5 | 82.2 | 54.5 | 65.4 | |
| HRNetInput Size=384×288, GFLOPs=16.0, Estimation Approach=Top-down, Flip test=true2026.03 | 58.6 | 67.4 | 70.1 | 77.3 | 58.6 | 69.2 | 72.7 | 78.3 | 51.6 | 60.4 | |
| RTMPose-mInput Size=256×192, GFLOPs=2.2, Estimation Approach=Top-down, Flip test=true2026.03 | 58.2 | 67.4 | 67.3 | 75 | 61.5 | 75.2 | 81.3 | 87.1 | 47.5 | 58.9 | |
| SimpleBaselineInput Size=384×288, GFLOPs=20.4, Estimation Approach=Top-down, Flip test=true2026.03 | 57.3 | 67.1 | 66.6 | 74.7 | 63.5 | 76.3 | 73.2 | 81.2 | 53.7 | 64.7 | |
| OpenPoseInput Size=N/A, GFLOPs=451.1, Estimation Approach=Whole-body, Flip test=true2026.03 | 44.2 | 52.3 | 56.3 | 61.2 | 53.2 | 64.5 | 76.5 | 84 | 38.6 | 43.3 | |
| AEInput Size=512×512, GFLOPs=212.4, Estimation Approach=Bottom-up, Flip test=true2026.03 | 44 | 54.5 | 58 | 66.1 | 57.7 | 72.5 | 58.8 | 65.4 | 48.1 | 57.4 | |
| SNInput Size=N/A, GFLOPs=272.3, Estimation Approach=Whole-body, Multi-scale testing=true, Flip test=true2026.03 | 32.7 | 45.6 | 42.7 | 58.3 | 9.9 | 36.9 | 64.9 | 69.7 | 40.8 | 58 | |
| PAFInput Size=512×512, GFLOPs=329.1, Estimation Approach=Bottom-up, Multi-scale testing=true, Flip test=true2026.03 | 29.5 | 40.5 | 38.1 | 52.6 | 5.3 | 27.8 | 65.6 | 70.1 | 35.9 | 52.8 |