Local and Global Fusion Network For Learned Image Compression

Convolution autoencoder is a widely utilized framework for learned image compression. However, it is facing performance bottleneck because the convolution with limited receptive field mainly extracts image local information. In this paper, we propose a novel neural network based image compression framework by removing both local and global redundancy. Herein, convolution autoencoder and Generative flow (Glow) are utilized to extract image local and global information respectively. Glow is a lossless invertible neural network and can facilitate global information extraction. Furthermore, we design a DenseNet module to fuse the local and global information extracted from convolution autoencoder and Glow. Extensive experimental results show that the proposed framework outperform the intra-frame coding of Versatile Video Coding (VVC) and state-of-the-art neural network based image compression methods.