Deep Image Compression with Iterative Non-Uniform Quantization

Image compression, which aims to represent an image with less storage space, is a classical problem in image processing. Recently, by training an encoder-quantizer-decoder network, deep convolutional neural networks (CNNs) have achieved promising results in image compression. As a nondifferentiable part of the compression system, quantizer is hard to be updated during the network training. Most of existing deep image compression methods adopt a uniform rounding function as the quantizer, which however restricts the capability and flexibility of CNNs in compressing complex image structures. In this paper, we present an iterative nonuniform quantization scheme for deep image compression. More specifically, we alternatively optimize the quantizer and encoder-decoder. When the encoder-decoder is fixed, a non-uniform quantizer is optimized based on the distribution of representation features. The encoder-decoder network is then updated by fixing the quantizer. Extensive experiments demonstrate the superior PSNR index of the proposed method to existing deep compressors and JPEG2000.

1. Introduction

With the explosive growth of portable imaging devices and social media (e.g., Facebook and Flickr), billions of images are shared daily on social networks. Image compression, especially lossy image compression, is a must to reduce the storage space and provide an economic solution to a wide range of image storage and transmission systems.