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 | SMPLify | Mean Reconstruction Error (mm) | 79.9 | — | Unverified |
| 2 | SMPLify (dense) | Mean Reconstruction Error (mm) | 74.5 | — | Unverified |
| 3 | Wang et al. | Mean Reconstruction Error (mm) | 71.3 | — | Unverified |
| 4 | Ours | Mean Reconstruction Error (mm) | 64 | — | Unverified |
| 5 | Simo-Serra et al. | Mean Reconstruction Error (mm) | 56.7 | — | Unverified |
| 6 | DSRF | Mean Reconstruction Error (mm) | 40.3 | — | Unverified |
| 7 | TGP | Mean Reconstruction Error (mm) | 39.1 | — | Unverified |
| 8 | Dual-source approach | Mean Reconstruction Error (mm) | 38.9 | — | Unverified |
| 9 | DMHSR(J,B,D) | Mean Reconstruction Error (mm) | 33.7 | — | Unverified |
| 10 | Recurrent 3D Pose Sequence Machines | Mean Reconstruction Error (mm) | 30.8 | — | Unverified |