Convolutional autoencoders are now at the forefront of image compression research. To improve their entropy coding, encoder output is typically analyzed with a second autoencoder to generate per-variable parametrized prior probability distributions. We instead propose a compression scheme that uses a single convolutional autoencoder and multiple learned prior distributions working as a competition of experts. Trained prior distributions are stored in a static table of cumulative distribution functions. During inference, this table is used by an entropy coder as a look-up-table to determine the best prior for each spatial location. Our method offers rate-distortion performance comparable to that obtained with a predicted parametrized prior with only a fraction of its entropy coding and decoding complexity.
@article{arxiv.2111.09172,
title = {End-to-end optimized image compression with competition of prior distributions},
author = {Benoit Brummer and Christophe De Vleeschouwer},
journal= {arXiv preprint arXiv:2111.09172},
year = {2021}
}