In this paper, we build autoencoder based pipelines for extreme end-to-end image compression based on Ball\'e's approach, which is the state-of-the-art open source implementation in image compression using deep learning. We deepened the network by adding one more hidden layer before each strided convolutional layer with exactly the same number of down-samplings and up-samplings. Our approach outperformed Ball\'e's approach, and achieved around 4.0% reduction in bits per pixel (bpp), 0.03% increase in multi-scale structural similarity (MS-SSIM), and only 0.47% decrease in peak signal-to-noise ratio (PSNR), It also outperforms all traditional image compression methods including JPEG2000 and HEIC by at least 20% in terms of compression efficiency at similar reconstruction image quality. Regarding encoding and decoding time, our approach takes similar amount of time compared with traditional methods with the support of GPU, which means it's almost ready for industrial applications.

中文翻译：

---

使用深度学习改进图像编码自动编码器

在本文中，我们基于 Ball\'e 的方法构建了基于自动编码器的管道，用于极端的端到端图像压缩，这是使用深度学习的最先进的图像压缩开源实现。我们通过在每个跨步卷积层之前添加一个隐藏层来加深网络，下采样和上采样的数量完全相同。我们的方法优于 Ball\'e 的方法，实现了每像素位数 (bpp) 减少约 4.0%，多尺度结构相似性 (MS-SSIM) 增加 0.03%，峰值信噪比仅降低 0.47%比 (PSNR)，在相似的重建图像质量下，它在压缩效率方面也比包括 JPEG2000 和 HEIC 在内的所有传统图像压缩方法至少高出 20%。关于编码和解码时间，