# 3D Human Pose Estimation with Siamese Equivariant Embedding

arXiv: https://arxiv.org/abs/1809.07217 · HTML: https://mlsanity.com/paper/1809.07217/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2018.

## Built on by (most cited first, 1 of 1)

- [Invariance Measures for Neural Networks](https://mlsanity.com/paper/2310.17404/) (2023)

## Abstract (arXiv)

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.