Generative Adversarial Graph Convolutional Networks for Human Action Synthesis
This addresses the challenge of generating realistic human actions for applications like animation or robotics, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of synthesizing realistic and diverse human body skeleton movements for specific actions, proposing Kinetic-GAN, which improves sample quality and diversity, notably surpassing state-of-the-art methods in distribution quality metrics and enabling synthesis of over 120 different actions.
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.