Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation

TL;DR

This paper introduces a deep structured-output learning framework for 3D human pose estimation from monocular images, achieving state-of-the-art results by jointly learning image and pose embeddings with a maximum-margin approach.

Contribution

It proposes a novel deep network architecture that combines structured-output learning with maximum-margin training for improved 3D human pose estimation.

Findings

Achieved state-of-the-art performance on Human3.6m dataset.

Demonstrated effective joint embedding of images and poses.

Visualized learned embedding space for pose and orientation.

Abstract

This paper focuses on structured-output learning using deep neural networks for 3D human pose estimation from monocular images. Our network takes an image and 3D pose as inputs and outputs a score value, which is high when the image-pose pair matches and low otherwise. The network structure consists of a convolutional neural network for image feature extraction, followed by two sub-networks for transforming the image features and pose into a joint embedding. The score function is then the dot-product between the image and pose embeddings. The image-pose embedding and score function are jointly trained using a maximum-margin cost function. Our proposed framework can be interpreted as a special form of structured support vector machines where the joint feature space is discriminatively learned using deep neural networks. We test our framework on the Human3.6m dataset and obtain state-of-the-art results compared to other recent methods. Finally, we present visualizations of the image-pose embedding space, demonstrating the network has learned a high-level embedding of body-orientation and pose-configuration.