Generating images with recurrent adversarial networks

02/16/2016 ∙ by Daniel Jiwoong Im, et al. ∙ 0

Gatys et al. (2015) showed that optimizing pixels to match features in a convolutional network with respect reference image features is a way to render images of high visual quality. We show that unrolling this gradient-based optimization yields a recurrent computation that creates images by incrementally adding onto a visual "canvas". We propose a recurrent generative model inspired by this view, and show that it can be trained using adversarial training to generate very good image samples. We also propose a way to quantitatively compare adversarial networks by having the generators and discriminators of these networks compete against each other.



There are no comments yet.


page 6

page 8

page 13

page 15

page 16

page 17

page 18

page 20

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.