Hand Pose Estimation on MSRA (leave-one-subject-out)
7.2Mean Error (mm)DenseReg
Evaluation Results
| Method | Links | |
|---|---|---|
| DenseRegInput=2D, Type=Detection-based (D)2021.08 | 7.2 | |
| HandFoldingNetInput=3D, Type=Regression-based (R)2021.08 | 7.34 | |
| JGR-P2OInput=2D, Type=Detection-based (D)2021.08 | 7.55 | |
| V2VInput=3D, Type=Detection-based (D)2021.08 | 7.59 | |
| Point-to-PointInput=3D, Type=Detection-based (D)2021.08 | 7.7 | |
| SHPR-NetInput=3D, Type=Regression-based (R)2021.08 | 7.76 | |
| CrossInfoNetInput=2D, Type=Regression-based (R)2021.08 | 7.86 | |
| HandPointNetInput=3D, Type=Regression-based (R)2021.08 | 8.5 | |
| Pose-RenInput=2D, Type=Regression-based (R)2021.08 | 8.65 | |
| DeepPrior++Input=2D, Type=Regression-based (R)2021.08 | 9.5 | |
| 3DCNNInput=3D, Type=Regression-based (R)2021.08 | 9.6 | |
| Ren-9x6x6Input=2D, Type=Regression-based (R)2021.08 | 9.7 |