# Generating images with recurrent adversarial networks

arXiv: https://arxiv.org/abs/1602.05110 · HTML: https://mlsanity.com/paper/1602.05110/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2016.

## Built on by (most cited first, 9 of 9)

- [Compositional Transformers for Scene Generation](https://mlsanity.com/paper/2111.08960/) (2021)
- [Generative adversarial networks in time series: A survey and taxonomy](https://mlsanity.com/paper/2107.11098/) (2021)
- [GAN Computers Generate Arts? A Survey on Visual Arts, Music, and Literary Text Generation using Generative Adversarial Network](https://mlsanity.com/paper/2108.03857/) (2021)
- [Learning-Driven Lossy Image Compression; A Comprehensive Survey](https://mlsanity.com/paper/2201.09240/) (2022)
- [A Realism Metric for Generated LiDAR Point Clouds](https://mlsanity.com/paper/2208.14958/) (2022)
- [Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey](https://mlsanity.com/paper/2111.13282/) (2021)
- [Quantifying point cloud realism through adversarially learned latent representations](https://mlsanity.com/paper/2109.11775/) (2021)
- [Geometric Generative Models based on Morphological Equivariant PDEs and GANs](https://mlsanity.com/paper/2403.14897/) (2024)
- [GM Score: Incorporating inter-class and intra-class generator diversity, discriminability of disentangled representation, and sample fidelity for evaluating GANs](https://mlsanity.com/paper/2112.06431/) (2021)

## Abstract (arXiv)

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.