Image Compression with Recurrent Neural Network and Generalized Divisive Normalization

TL;DR

This paper introduces a novel image compression framework using recurrent neural networks and generalized divisive normalization, achieving superior quality over traditional codecs and existing deep learning methods.

Contribution

It develops new analysis and synthesis blocks with GDN and employs RNNs and LSTM for efficient quantization and residual encoding, enhancing compression performance.

Findings

Outperforms existing deep learning and standard codecs in image similarity.

Uses a novel combination of RNN, LSTM, and GDN for improved compression.

Achieves better quality at comparable or lower bitrates.

Abstract

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 https://khawar512.github.io/cvpr/