End-to-End Optimized Image Compression With Competition of Prior Distributions

Benoit Brummer, Christophe De Vleeschouwer; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 1890-1894

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.