Generating images with recurrent adversarial networks
This work addresses image generation for computer vision applications, presenting an incremental improvement by combining recurrent structures with adversarial training.
The authors tackled image generation by proposing a recurrent generative model trained with adversarial training, which produced very good image samples and introduced a quantitative comparison method for adversarial networks.
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.