3DCrowdNet (HigherHRNet)

Reported on 5 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

3D Human Pose EstimationonMuPoTS-3D
3DPCK· 2021-04-15
72.7
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes arXiv:2104.07300
Pose EstimationonMuPoTS-3D
3DPCK· 2021-04-15
72.7
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes arXiv:2104.07300
3D Multi-Person Pose EstimationonMuPoTS-3D
3DPCK· 2021-04-15
72.7
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes arXiv:2104.07300

3DonMuPoTS-3D
3DPCK· 2021-04-15
72.7
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes arXiv:2104.07300

1 Image, 2*2 StitchionMuPoTS-3D
3DPCK· 2021-04-15
72.7
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes arXiv:2104.07300