Generative Adversarial Graph Convolutional Networks for Human Action Synthesis

Synthesising the spatial and temporal dynamics of the human body skeleton remains a challenging task, not only in terms of the quality of the generated shapes, but also of their diversity, particularly to synthesise realistic body movements of a specific action (action conditioning). In this paper, we propose Kinetic-GAN, a novel architecture that leverages the benefits of Generative Adversarial Networks and Graph Convolutional Networks to synthesise the kinetics of the human body. The proposed adversarial architecture can condition up to 120 different actions over local and global body movements while improving sample quality and diversity through latent space disentanglement and stochastic variations. Our experiments were carried out in three well-known datasets, where Kinetic-GAN notably surpasses the state-of-the-art methods in terms of distribution quality metrics while having the ability to synthesise more than one order of magnitude regarding the number of different actions. Our code and models are publicly available at https://github.com/DegardinBruno/Kinetic-GAN.

1. Introduction

Human behaviour analysis through skeleton-based data has been widely investigated for decades. The advent of deep learning-based architectures increased its popularity even more, mainly due to the robustness of skeleton data in handling dynamic circumstances, appearance variations, and cluttered backgrounds. Over the last decade, the rise of data-driven approaches highly correlates performance with the scale of the learning set. Hence, generating high-quality synthetic human actions can address the problem of limited data. However, existing methods are still severely limited, particularly in conditioning desirable actions and considering the generation at the global movement level.