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/IKOL

IKOL

Reported on 24 benchmarks across 4 tasks · 1 paper

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

Computer Vision12 results

3D Human Pose EstimationonMPI-INF-3DHP
AUC· 2023-02-02
48.1
best: 87.7 (TCPFormer (T=81))
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
3D Human Pose EstimationonMPI-INF-3DHP
MPJPE· 2023-02-02
88.8
best: 124.7 (VNect (Augm.))
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
3D Human Pose EstimationonMPI-INF-3DHP
PCK· 2023-02-02
87.9
best: 99.37 (LMT R152 384x384)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
3D Human Pose Estimationon3DPW
MPJPE· 2023-02-02
71.1
best: 130 (HMR)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
3D Human Pose Estimationon3DPW
MPVPE· 2023-02-02
84.1
best: 119.3 (BMP)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
3D Human Pose Estimationon3DPW
PA-MPJPE· 2023-02-02
44.5
best: 157 (Simple-baseline)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
Pose EstimationonMPI-INF-3DHP
AUC· 2023-02-02
48.1
best: 87.7 (TCPFormer (T=81))
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
Pose EstimationonMPI-INF-3DHP
MPJPE· 2023-02-02
88.8
best: 124.7 (VNect (Augm.))
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
Pose EstimationonMPI-INF-3DHP
PCK· 2023-02-02
87.9
best: 99.37 (LMT R152 384x384)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
Pose Estimationon3DPW
MPJPE· 2023-02-02
71.1
best: 130 (HMR)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
Pose Estimationon3DPW
MPVPE· 2023-02-02
84.1
best: 119.3 (BMP)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
Pose Estimationon3DPW
PA-MPJPE· 2023-02-02
44.5
best: 157 (Simple-baseline)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058

Methodology6 results

3DonMPI-INF-3DHP
AUC· 2023-02-02
48.1
best: 87.7 (TCPFormer (T=81))
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
3DonMPI-INF-3DHP
MPJPE· 2023-02-02
88.8
best: 124.7 (VNect (Augm.))
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
3DonMPI-INF-3DHP
PCK· 2023-02-02
87.9
best: 99.37 (LMT R152 384x384)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
3Don3DPW
MPJPE· 2023-02-02
71.1
best: 130 (HMR)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
3Don3DPW
MPVPE· 2023-02-02
84.1
best: 119.3 (BMP)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
3Don3DPW
PA-MPJPE· 2023-02-02
44.5
best: 157 (Simple-baseline)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058

Audio6 results

1 Image, 2*2 StitchionMPI-INF-3DHP
AUC· 2023-02-02
48.1
best: 87.7 (TCPFormer (T=81))
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
1 Image, 2*2 StitchionMPI-INF-3DHP
MPJPE· 2023-02-02
88.8
best: 124.7 (VNect (Augm.))
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
1 Image, 2*2 StitchionMPI-INF-3DHP
PCK· 2023-02-02
87.9
best: 99.37 (LMT R152 384x384)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
1 Image, 2*2 Stitchion3DPW
MPJPE· 2023-02-02
71.1
best: 130 (HMR)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
1 Image, 2*2 Stitchion3DPW
MPVPE· 2023-02-02
84.1
best: 119.3 (BMP)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058
1 Image, 2*2 Stitchion3DPW
PA-MPJPE· 2023-02-02
44.5
best: 157 (Simple-baseline)
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation arXiv:2302.01058