Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

TL;DR

This paper presents a novel generative image model that combines a Laplacian pyramid framework with adversarial networks to produce high-quality, natural images in a coarse-to-fine manner, outperforming previous methods.

Contribution

It introduces a multi-scale generative model using separate GANs at each pyramid level, enhancing image quality and realism over existing approaches.

Findings

Samples are mistaken for real images 40% of the time in human evaluations.

Model outperforms baseline GANs in image realism.

Effective on high-resolution datasets like LSUN.

Abstract

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.