Generative Adversarial Networks for Extreme Learned Image Compression
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.
Cite
Text
Agustsson et al. "Generative Adversarial Networks for Extreme Learned Image Compression." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00031Markdown
[Agustsson et al. "Generative Adversarial Networks for Extreme Learned Image Compression." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/agustsson2019iccv-generative/) doi:10.1109/ICCV.2019.00031BibTeX
@inproceedings{agustsson2019iccv-generative,
title = {{Generative Adversarial Networks for Extreme Learned Image Compression}},
author = {Agustsson, Eirikur and Tschannen, Michael and Mentzer, Fabian and Timofte, Radu and Van Gool, Luc},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/ICCV.2019.00031},
url = {https://mlanthology.org/iccv/2019/agustsson2019iccv-generative/}
}