Deep Probabilistic Modeling of Natural Images using a Pyramid Decomposition

We introduce a new technique for probabilistic modeling of natural images that combines the advantages of classic multi-scale and modern deep learning models. By explicitly representing natural images at different scales we derive a model that can capture high level image structure in a computationally efficient way. We show experimentally that our model achieves new state-of-the-art image modeling performance on the CIFAR-10 dataset and at the same time is much faster than competitive models. We also evaluate the proposed technique on a human faces dataset and demonstrate the potential of our model to generate nearly photorealistic face samples.