Image compression is a method to remove spatial redundancy between adjacent
pixels and reconstruct a high-quality image. In the past few years, deep
learning has gained huge attention from the research community and produced
promising image reconstruction results. Therefore, recent methods focused on
developing deeper and more complex networks, which significantly increased
network complexity. In this paper, two effective novel blocks are developed:
analysis and synthesis block that employs the convolution layer and Generalized
Divisive Normalization (GDN) in the variable-rate encoder and decoder side. Our
network utilizes a pixel RNN approach for quantization. Furthermore, to improve
the whole network, we encode a residual image using LSTM cells to reduce
unnecessary information. Experimental results demonstrated that the proposed
variable-rate framework with novel blocks outperforms existing methods and
standard image codecs, such as George's ~\cite{002} and JPEG in terms of image
similarity. The project page along with code and models are available at
this https URL

本文针对图像压缩中的深度学习方法进行了研究，提出了一种基于变速率编码器和解码器的分析和合成块，利用卷积层和广义除法归一化 (GDN)，并使用像素 RNN 方法进行量化。实验结果表明，所提出的可变速率框架结构，能够优于现有方法和标准图像编解码器，如 George 和 JPEG 等。