Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation

TL;DR

This paper introduces a hybrid deep learning and graphical model architecture for human pose estimation, leveraging structural constraints to improve accuracy in monocular images.

Contribution

It presents a novel joint training approach for combining convolutional networks with Markov Random Fields for pose estimation.

Findings

Significant performance improvement over existing methods

Effective exploitation of geometric constraints

Outperforms state-of-the-art techniques

Abstract

This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training of these two model paradigms improves performance and allows us to significantly outperform existing state-of-the-art techniques.