Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MUG

MUG

Reported on 21 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 Vision11 results

3D Human Pose EstimationonPanoptic
Average MPJPE (mm)· 2022-05-25
127.8
best: 135.4 (BMP)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
3D Human Pose Estimationon3DPW
MPJPE· 2022-05-25
87
best: 130 (HMR)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
3D Human Pose Estimationon3DPW
MPVPE· 2022-05-25
106.2
best: 119.3 (BMP)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
3D Human Pose Estimationon3DPW
PA-MPJPE· 2022-05-25
60.5
best: 157 (Simple-baseline)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
3D Human Pose EstimationonMuPoTS-3D
3DPCK· 2022-05-25
76.27
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
Pose EstimationonPanoptic
Average MPJPE (mm)· 2022-05-25
127.8
best: 135.4 (BMP)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
Pose Estimationon3DPW
MPJPE· 2022-05-25
87
best: 130 (HMR)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
Pose Estimationon3DPW
MPVPE· 2022-05-25
106.2
best: 119.3 (BMP)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
Pose Estimationon3DPW
PA-MPJPE· 2022-05-25
60.5
best: 157 (Simple-baseline)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
Pose EstimationonMuPoTS-3D
3DPCK· 2022-05-25
76.27
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
3D Multi-Person Pose EstimationonMuPoTS-3D
3DPCK· 2022-05-25
76.27
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583

Methodology5 results

3DonPanoptic
Average MPJPE (mm)· 2022-05-25
127.8
best: 135.4 (BMP)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
3Don3DPW
MPJPE· 2022-05-25
87
best: 130 (HMR)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
3Don3DPW
MPVPE· 2022-05-25
106.2
best: 119.3 (BMP)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
3Don3DPW
PA-MPJPE· 2022-05-25
60.5
best: 157 (Simple-baseline)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
3DonMuPoTS-3D
3DPCK· 2022-05-25
76.27
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583

Audio5 results

1 Image, 2*2 StitchionPanoptic
Average MPJPE (mm)· 2022-05-25
127.8
best: 135.4 (BMP)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
1 Image, 2*2 Stitchion3DPW
MPJPE· 2022-05-25
87
best: 130 (HMR)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
1 Image, 2*2 Stitchion3DPW
MPVPE· 2022-05-25
106.2
best: 119.3 (BMP)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
1 Image, 2*2 Stitchion3DPW
PA-MPJPE· 2022-05-25
60.5
best: 157 (Simple-baseline)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583
1 Image, 2*2 StitchionMuPoTS-3D
3DPCK· 2022-05-25
76.27
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose arXiv:2205.12583