Generative Adversarial Graph Convolutional Networks for Human Action Synthesis

TL;DR

This paper introduces Kinetic-GAN, a novel generative model combining GANs and GCNs to synthesize diverse, realistic human body movements conditioned on multiple actions, outperforming existing methods in quality and diversity.

Contribution

The paper presents Kinetic-GAN, a new architecture that effectively synthesizes human action sequences with high diversity and quality, conditioned on numerous actions, using a combination of GANs and graph convolutional networks.

Findings

Outperforms state-of-the-art in distribution quality metrics

Synthesizes over ten times more actions than previous methods

Successfully conditions on up to 120 different actions

Abstract

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.