Generating images with recurrent adversarial networks

2016/02/16 by Im, Daniel Jiwoong, Kim, Chris Dongjoo, Jiang, Hui +1
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.1602.05110

Abstract

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.

Related

• Generating Images Part by Part with Composite Generative Adversarial Networks
• Optimizing the Latent Space of Generative Networks
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial\n Networks
• LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation