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/GFPose (HPJ2D-000, S=200)

GFPose (HPJ2D-000, S=200)

Reported on 16 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 Vision8 results

3D Human Pose EstimationonHuman3.6M
Using 2D ground-truth joints· 2022-12-16
16.9
SOTA
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
Pose EstimationonHuman3.6M
Using 2D ground-truth joints· 2022-12-16
16.9
SOTA
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
3D Human Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2022-12-16
35.6
best: 131.7 (Rhodin et al.)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
3D Human Pose EstimationonHuman3.6M
Average PMPJPE (mm)· 2022-12-16
30.5
best: 44.3 (Li et al.)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
3D Human Pose EstimationonMPI-INF-3DHP
PCK· 2022-12-16
86.9
best: 99.37 (LMT R152 384x384)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
Pose EstimationonHuman3.6M
Average MPJPE (mm)· 2022-12-16
35.6
best: 131.7 (Rhodin et al.)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
Pose EstimationonHuman3.6M
Average PMPJPE (mm)· 2022-12-16
30.5
best: 44.3 (Li et al.)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
Pose EstimationonMPI-INF-3DHP
PCK· 2022-12-16
86.9
best: 99.37 (LMT R152 384x384)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641

Methodology4 results

3DonHuman3.6M
Using 2D ground-truth joints· 2022-12-16
16.9
SOTA
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
3DonHuman3.6M
Average MPJPE (mm)· 2022-12-16
35.6
best: 131.7 (Rhodin et al.)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
3DonHuman3.6M
Average PMPJPE (mm)· 2022-12-16
30.5
best: 44.3 (Li et al.)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
3DonMPI-INF-3DHP
PCK· 2022-12-16
86.9
best: 99.37 (LMT R152 384x384)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641

Audio4 results

1 Image, 2*2 StitchionHuman3.6M
Using 2D ground-truth joints· 2022-12-16
16.9
SOTA
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
1 Image, 2*2 StitchionHuman3.6M
Average MPJPE (mm)· 2022-12-16
35.6
best: 131.7 (Rhodin et al.)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
1 Image, 2*2 StitchionHuman3.6M
Average PMPJPE (mm)· 2022-12-16
30.5
best: 44.3 (Li et al.)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641
1 Image, 2*2 StitchionMPI-INF-3DHP
PCK· 2022-12-16
86.9
best: 99.37 (LMT R152 384x384)
GFPose: Learning 3D Human Pose Prior with Gradient Fields arXiv:2212.08641