论文标题
高保真生成图像压缩
High-Fidelity Generative Image Compression
论文作者
论文摘要
我们广泛研究了如何结合生成的对抗网络并学习的压缩以获得最新的生成损耗压缩系统。特别是，我们研究了归一化层，生成器和判别器架构，培训策略以及知觉损失。与以前的工作相反，i）我们获得了与输入相似的视觉令人愉悦的重建，ii）我们在广泛的比特率中运行； iii）我们的方法可以应用于高分辨率图像。我们通过通过各种感知指标和用户研究来定量评估我们的方法，弥合利率 - 缺陷感知理论与实践之间的差距。研究表明，即使它们使用超过2倍的比特率，我们的方法也比以前的方法更喜欢。
We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system. In particular, we investigate normalization layers, generator and discriminator architectures, training strategies, as well as perceptual losses. In contrast to previous work, i) we obtain visually pleasing reconstructions that are perceptually similar to the input, ii) we operate in a broad range of bitrates, and iii) our approach can be applied to high-resolution images. We bridge the gap between rate-distortion-perception theory and practice by evaluating our approach both quantitatively with various perceptual metrics, and with a user study. The study shows that our method is preferred to previous approaches even if they use more than 2x the bitrate.
