A survey of Image Compression Algorithms based on Deep Learning

Abstract

Abstract Images can carry more information than words, but the data space of images format is much larger than the text format when they are containing the same information. Therefore, how to efficiently compress images to improve their storability and transmissibility is one of the key research issues in the field of computer vision. Through consulting the relevant literature, this paper analyzes the development process of the current image compression technology, and introduces traditional compression methods and deep learning compression methods, while focusing on the compression methods based on deep learning. Through comparative experiments, this paper analyzes the performance of various types of neural networks in image compression tasks, and summarizes the advantages and disadvantages of various types of neural networks in compression tasks.