End-to-end optimized image compression with competition of prior distributions

Brummer, Benoit;De Vleeschouwer, Christophe
(2021) 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) — Location: Nashville, TN, USA (19.June.2021)

Files

clic.pdf
  • Open Access
  • Adobe PDF
  • 8.65 MB
Download

Details

Authors
Abstract
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.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Brummer, B., & De Vleeschouwer, C. (2021). End-to-end optimized image compression with competition of prior distributions. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 1(1), 1890-1894. https://doi.org/10.1109/cvprw53098.2021.00212 (Original work published 2021)