Capsules as viewpoint learners for human pose estimation

TL;DR

This paper introduces a novel capsule network architecture for human pose estimation that achieves viewpoint equivariance, leading to better generalization across different camera angles and reduced data dependency.

Contribution

The work presents a new end-to-end capsule autoencoder with Variational Bayes routing for human pose estimation, improving viewpoint generalization and inference speed.

Findings

State-of-the-art results on multiple datasets

Enhanced generalization to unseen viewpoints

Lower data dependency and faster inference

Abstract

The task of human pose estimation (HPE) deals with the ill-posed problem of estimating the 3D position of human joints directly from images and videos. In recent literature, most of the works tackle the problem mostly by using convolutional neural networks (CNNs), which are capable of achieving state-of-the-art results in most datasets. We show how most neural networks are not able to generalize well when the camera is subject to significant viewpoint changes. This behaviour emerges because CNNs lack the capability of modelling viewpoint equivariance, while they rather rely on viewpoint invariance, resulting in high data dependency. Recently, capsule networks (CapsNets) have been proposed in the multi-class classification field as a solution to the viewpoint equivariance issue, reducing both the size and complexity of both the training datasets and the network itself. In this work, we show how capsule networks can be adopted to achieve viewpoint equivariance in human pose estimation. We propose a novel end-to-end viewpoint-equivariant capsule autoencoder that employs a fast Variational Bayes routing and matrix capsules. We achieve state-of-the-art results for multiple tasks and datasets while retaining other desirable properties, such as greater generalization capabilities when changing viewpoints, lower data dependency and fast inference. Additionally, by modelling each joint as a capsule, the hierarchical and geometrical structure of the overall pose is retained in the feature space, independently from the viewpoint. We further test our network on multiple datasets, both in the RGB and depth domain, from seen and unseen viewpoints and in the viewpoint transfer task.