Learning-Based Image Compression using Convolutional Autoencoder and Wavelet Decomposition

In this paper, a learning-based image compression method that employs wavelet decomposition as a preprocessing step is presented. The proposed convolutional autoencoder is trained end-to-end to yield a target bitrate smaller than 0.15 bits per pixel across the full CLIC2019 test set. Objective results show that the proposed model is able to outperform legacy JPEG compression, as well as a similar convolutional autoencoder that excludes the proposed preprocessing. The presented architecture shows that wavelet decomposition is beneficial in adjusting the frequency characteristics of the compressed image and helps increase the performance of learning-based image compression models.