Generative adversarial networks for extreme learned image compression


Eirikur Agustsson, Michael Tschannen, Fabian Mentzer, Radu Timofte, and Luc Van Gool


preprint, 2018, submitted.

[BibTeX, LaTeX, and HTML Reference]


We propose a framework for extreme learned image compression based on Generative Adversarial Networks (GANs), obtaining visually pleasing images at significantly lower bitrates than previous methods. This is made possible through our GAN formulation of learned compression combined with a generator/decoder which operates on the full-resolution image and is trained in combination with a multi-scale discriminator. Additionally, our method can fully synthesize unimportant regions in the decoded image such as streets and trees from a semantic label map extracted from the original image, therefore only requiring the storage of the preserved region and the semantic label map. A user study confirms that for low bitrates, our approach significantly outperforms state-of-the-art methods, saving up to 67% compared to the next-best method BPG.


EA, MT, and FM contributed equally. Project website:

Download this document:


Copyright Notice: © 2018 E. Agustsson, M. Tschannen, F. Mentzer, R. Timofte, and L. Van Gool.

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.