Generative models are a fast advancing area of study and research. As we proceed to advance these models and grow the training and datasets, we can expect to generate data examples that depict completely believable images, finally. This can be used in several applications such as image denoising, painting, structured prediction, and exploration in reinforcement learning.
The deeper promise of this effort is that, in the process of building generative models, we will enrich the computer with an understanding of the world and what elements it is made up of.
