3D Human Pose Estimation with Siamese Equivariant Embedding

19 Sep 2018  ·  Márton Véges, Viktor Varga, András Lőrincz ·

In monocular 3D human pose estimation a common setup is to first detect 2D positions and then lift the detection into 3D coordinates. Many algorithms suffer from overfitting to camera positions in the training set. We propose a siamese architecture that learns a rotation equivariant hidden representation to reduce the need for data augmentation. Our method is evaluated on multiple databases with different base networks and shows a consistent improvement of error metrics. It achieves state-of-the-art cross-camera error rate among algorithms that use estimated 2D joint coordinates only.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation Human3.6M Siamese Equivariant Embedding Average MPJPE (mm) 61.1 # 205

Methods


No methods listed for this paper. Add relevant methods here