Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from image to 3D pose, which ignores the dependencies between human joints, or model these dependencies via a max-margin structured learning framework, which involves a high computational cost at inference time. In this paper, we introduce a Deep Learning regression architecture for structured prediction of 3D human pose from monocular images that relies on an overcomplete auto-encoder to learn a high-dimensional latent pose representation and account for joint dependencies. We demonstrate that our approach outperforms state-of-the-art ones both in terms of structure preservation and prediction accuracy.
@article{arxiv.1605.05180,
title = {Structured Prediction of 3D Human Pose with Deep Neural Networks},
author = {Bugra Tekin and Isinsu Katircioglu and Mathieu Salzmann and Vincent Lepetit and Pascal Fua},
journal= {arXiv preprint arXiv:1605.05180},
year = {2016}
}