In this paper we introduce a generative parametric model capable of producing high quality samples of natural images. Our approach uses a cascade of convolutional networks within a Laplacian pyramid framework to generate images in a coarse-to-fine fashion. At each level of the pyramid, a separate generative convnet model is trained using the Generative Adversarial Nets (GAN) approach (Goodfellow et al.). Samples drawn from our model are of significantly higher quality than alternate approaches. In a quantitative assessment by human evaluators, our CIFAR10 samples were mistaken for real images around 40% of the time, compared to 10% for samples drawn from a GAN baseline model. We also show samples from models trained on the higher resolution images of the LSUN scene dataset.
@article{arxiv.1506.05751,
title = {Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks},
author = {Emily Denton and Soumith Chintala and Arthur Szlam and Rob Fergus},
journal= {arXiv preprint arXiv:1506.05751},
year = {2015}
}