Pose Estimation On Itop Front View
評価指標
Mean mAP
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Mean mAP | Paper Title | Repository |
|---|---|---|---|
| A2J | 88.0 | A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image | |
| V2V-PoseNet | 88.74 | V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map | |
| Multi-task learning + viewpoint invariance | 77.4 | Towards Viewpoint Invariant 3D Human Pose Estimation | |
| SPiKE | 89.19 | SPiKE: 3D Human Pose from Point Cloud Sequences | |
| REN | 84.9 | Towards Good Practices for Deep 3D Hand Pose Estimation | - |
| AdaPose | 93.38 | Sequential 3D Human Pose Estimation Using Adaptive Point Cloud Sampling Strategy | |
| DECA-D3 | 88.75 | DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders |
0 of 7 row(s) selected.