Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
This work addresses the challenge of realistic image generation for computer vision applications, representing a significant improvement over prior methods.
The paper tackles the problem of generating high-quality natural images by introducing a generative model that uses a Laplacian pyramid of adversarial networks, achieving samples that human evaluators mistook for real images 40% of the time on CIFAR10 compared to 10% for a baseline.
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.