期刊
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
卷 -, 期 -, 页码 221-231出版社
IEEE COMPUTER SOC
DOI: 10.1109/ICCV.2019.00031
关键词
-
资金
- ETH Zurich General Fund
- Nvidia GPU hardware grant
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据