Image compression has been investigated for many decades. Recently, deep learning approaches have achieved a great success in many computer vision tasks, and are gradually used in image compression. In this paper, we develop three overall compression architectures based on convolutional autoencoders (CAEs), generative adversarial networks (GANs) as well as super-resolution (SR), and present a comprehensive performance comparison. According to experimental results, CAEs achieve better coding efficiency than JPEG by extracting compact features. GANs show potential advantages on large compression ratio and high subjective quality reconstruction. Super-resolution achieves the best rate-distortion (RD) performance among them, which is comparable to BPG.
@article{arxiv.1807.00270,
title = {Performance Comparison of Convolutional AutoEncoders, Generative Adversarial Networks and Super-Resolution for Image Compression},
author = {Zhengxue Cheng and Heming Sun and Masaru Takeuchi and Jiro Katto},
journal= {arXiv preprint arXiv:1807.00270},
year = {2018}
}
Comments
Submitted to CVPR Workshop and Challenge On Learned Image Compression (CLIC) 2018