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 | CanonPose | Average MPJPE (mm) | 74.3 | — | Unverified |
| 2 | VIBE | Average MPJPE (mm) | 65.6 | — | Unverified |
| 3 | VoxelKeypointFusion (transfer) | Average MPJPE (mm) | 64.3 | — | Unverified |
| 4 | SIM (SH detections FT) (MA) | Average MPJPE (mm) | 62.9 | — | Unverified |
| 5 | 2D-3D Lifting self-supervised | Average MPJPE (mm) | 62 | — | Unverified |
| 6 | Probabilistic Monocular (T=1) | Average MPJPE (mm) | 61.8 | — | Unverified |
| 7 | TAPE (T=16) | Average MPJPE (mm) | 60 | — | Unverified |
| 8 | Sequence-to-sequence network | Average MPJPE (mm) | 58.5 | — | Unverified |
| 9 | Stereoscopic View Synthesis Subnetwork | Average MPJPE (mm) | 58 | — | Unverified |
| 10 | SemGCN | Average MPJPE (mm) | 57.6 | — | Unverified |