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 | MUG | Average MPJPE (mm) | 127.8 | — | Unverified |
| 2 | ROMP (ResNet-50) | Average MPJPE (mm) | 127.6 | — | Unverified |
| 3 | InstanceHMR | Average MPJPE (mm) | 126.1 | — | Unverified |
| 4 | LoCO | Average MPJPE (mm) | 69 | — | Unverified |
| 5 | TesseTrack Monocular | Average MPJPE (mm) | 18.9 | — | Unverified |
| 6 | VTP | Average MPJPE (mm) | 17.62 | — | Unverified |
| 7 | Learnable Triangulation of Human Pose | Average MPJPE (mm) | 13.7 | — | Unverified |
| 8 | AdaFuse | Average MPJPE (mm) | 13.55 | — | Unverified |
| 9 | TesseTrack Multi-View (5 views) | Average MPJPE (mm) | 7.3 | — | Unverified |