3D Human Pose Estimation
3D Human Pose Estimation is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.
Papers
Showing 1–10 of 665 papers
All datasets3DPWMPI-INF-3DHPHuman3.6MHumanEva-IH3WBTotal CaptureEMDBAGORAPanopticSurreal3D Poses in the Wild ChallengeAIST++
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | ROS node wrapping | Average MPJPE (mm) | 112 | — | Unverified |
| 2 | PVH | Average MPJPE (mm) | 107 | — | Unverified |
| 3 | Tri-CPM | Average MPJPE (mm) | 99 | — | Unverified |
| 4 | IMUPVH | Average MPJPE (mm) | 70 | — | Unverified |
| 5 | Single-RPSM | Average MPJPE (mm) | 41 | — | Unverified |
| 6 | AutoEnc | Average MPJPE (mm) | 35 | — | Unverified |
| 7 | DeepFuse-Vision Only | Average MPJPE (mm) | 32.7 | — | Unverified |
| 8 | MTF-Transformer (M=0.4, T=7) | Average MPJPE (mm) | 29.2 | — | Unverified |
| 9 | Fusion-RPSM | Average MPJPE (mm) | 29 | — | Unverified |
| 10 | DeepFuse-IMU | Average MPJPE (mm) | 28.9 | — | Unverified |