Generative Adversarial Networks for Extreme Learned Image Compression

Eirikur Agustsson, Michael Tschannen, Fabian Mentzer, Radu Timofte, Luc Van Gool; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 221-231

Abstract


We present a learned image compression system based on GANs, operating at extremely low bitrates. Our proposed framework combines an encoder, decoder/generator and a multi-scale discriminator, which we train jointly for a generative learned compression objective. The model synthesizes details it cannot afford to store, obtaining visually pleasing results at bitrates where previous methods fail and show strong artifacts. Furthermore, if a semantic label map of the original image is available, our method can fully synthesize unimportant regions in the decoded image such as streets and trees from the label map, proportionally reducing the storage cost. A user study confirms that for low bitrates, our approach is preferred to state-of-the-art methods, even when they use more than double the bits.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Agustsson_2019_ICCV,
author = {Agustsson, Eirikur and Tschannen, Michael and Mentzer, Fabian and Timofte, Radu and Gool, Luc Van},
title = {Generative Adversarial Networks for Extreme Learned Image Compression},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}