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/SMPL-MDN (by 3D Multi-bodies)

SMPL-MDN (by 3D Multi-bodies)

Reported on 20 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Computer Vision10 results

3D Human Pose EstimationonAH36M
Best-Hypothesis MPJPE (n = 25)· 2019-04-11
91.5
best: 109.7 (SMPL-CVAE)
SOTA
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
Pose EstimationonAH36M
Best-Hypothesis MPJPE (n = 25)· 2019-04-11
91.5
best: 109.7 (SMPL-CVAE)
SOTA
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3D Human Pose EstimationonAH36M
Best-Hypothesis PMPJPE (n = 25)· 2019-04-11
69.5
best: 85.2 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3D Human Pose EstimationonAH36M
H36M PMPJPE (n = 1)· 2019-04-11
44.8
best: 67.4 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3D Human Pose EstimationonAH36M
H36M PMPJPE (n = 25)· 2019-04-11
42.7
best: 67.4 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3D Human Pose EstimationonAH36M
Most-Likely Hypothesis PMPJPE (n = 1)· 2019-04-11
74.7
best: 85.2 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
Pose EstimationonAH36M
Best-Hypothesis PMPJPE (n = 25)· 2019-04-11
69.5
best: 85.2 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
Pose EstimationonAH36M
H36M PMPJPE (n = 1)· 2019-04-11
44.8
best: 67.4 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
Pose EstimationonAH36M
H36M PMPJPE (n = 25)· 2019-04-11
42.7
best: 67.4 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
Pose EstimationonAH36M
Most-Likely Hypothesis PMPJPE (n = 1)· 2019-04-11
74.7
best: 85.2 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547

Methodology5 results

3DonAH36M
Best-Hypothesis MPJPE (n = 25)· 2019-04-11
91.5
best: 109.7 (SMPL-CVAE)
SOTA
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3DonAH36M
Best-Hypothesis PMPJPE (n = 25)· 2019-04-11
69.5
best: 85.2 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3DonAH36M
H36M PMPJPE (n = 1)· 2019-04-11
44.8
best: 67.4 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3DonAH36M
H36M PMPJPE (n = 25)· 2019-04-11
42.7
best: 67.4 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
3DonAH36M
Most-Likely Hypothesis PMPJPE (n = 1)· 2019-04-11
74.7
best: 85.2 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547

Audio5 results

1 Image, 2*2 StitchionAH36M
Best-Hypothesis MPJPE (n = 25)· 2019-04-11
91.5
best: 109.7 (SMPL-CVAE)
SOTA
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
1 Image, 2*2 StitchionAH36M
Best-Hypothesis PMPJPE (n = 25)· 2019-04-11
69.5
best: 85.2 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
1 Image, 2*2 StitchionAH36M
H36M PMPJPE (n = 1)· 2019-04-11
44.8
best: 67.4 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
1 Image, 2*2 StitchionAH36M
H36M PMPJPE (n = 25)· 2019-04-11
42.7
best: 67.4 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547
1 Image, 2*2 StitchionAH36M
Most-Likely Hypothesis PMPJPE (n = 1)· 2019-04-11
74.7
best: 85.2 (HMR (2D Vis, by MHEntropy))
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network arXiv:1904.05547