Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
Emily L Denton, Soumith Chintala, arthur szlam, Rob Fergus
Abstract
In this paper we introduce a generative model capable of producing high quality samples of natural images. Our approach uses a cascade of convolutional networks (convnets) 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. Samples drawn from our model are of significantly higher quality than existing models. In a quantitive assessment by human evaluators our CIFAR10 samples were mistaken for real images around 40% of the time, compared to 10% for GAN samples. We also show samples from more diverse datasets such as STL10 and LSUN.
BibTeX
@inproceedings{NIPS2015_aa169b49,
author = {Denton, Emily L and Chintala, Soumith and szlam, arthur and Fergus, Rob},
booktitle = {Advances in Neural Information Processing Systems},
editor = {C. Cortes and N. Lawrence and D. Lee and M. Sugiyama and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks},
url = {https://proceedings.neurips.cc/paper_files/paper/2015/file/aa169b49b583a2b5af89203c2b78c67c-Paper.pdf},
volume = {28},
year = {2015}
}