Recently, generative adversarial networks (GAN) have shown superior image data augmentation performance, but their suitability in gesture synthesis has received inadequate attention.  ...  We find that DeepNAG outperforms DeepGAN in accuracy, training time (up to 17x faster), and realism, thereby opening the door to a new line of research in generator network design and training for gesture  ...  Non-Adversarial Gesture Generation Although DeepGAN shows promising results (see Section 4), it demonstrated a few shortcomings early on.  ...