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 | HMR | B-NMVE | 217 | — | Unverified |
| 2 | SPIN | B-NMVE | 216.3 | — | Unverified |
| 3 | PARE | B-NMVE | 167.7 | — | Unverified |
| 4 | SPEC | B-NMVE | 126.8 | — | Unverified |
| 5 | Multi-Person 3D Pose and Shape Estimationvia Inverse Kinematics and Refinement | B-NMVE | 104.5 | — | Unverified |
| 6 | PyMAF-X | B-NMVE | 94.4 | — | Unverified |
| 7 | PyMAF | B-NMVE | 87.3 | — | Unverified |
| 8 | HybrIK | B-NMVE | 81.2 | — | Unverified |
| 9 | HybrIK-X | B-NMVE | 73.7 | — | Unverified |
| 10 | W-HMR | B-NMVE | 70.4 | — | Unverified |