Binary Probability Model for Learning Based Image Compression - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Binary Probability Model for Learning Based Image Compression


In this paper, we propose to enhance learned image compression systems with a richer probability model for the latent variables. Previous works model the latents with a Gaussian or a Laplace distribution. Inspired by binary arithmetic coding , we propose to signal the latents with three binary values and one integer, with different probability models. A relaxation method is designed to perform gradient-based training. The richer probability model results in a better entropy coding leading to lower rate. Experiments under the Challenge on Learned Image Compression (CLIC) test conditions demonstrate that this method achieves 18 % rate saving compared to Gaussian or Laplace models.
Fichier principal
Vignette du fichier
binarisation_article.pdf (1.8 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02476067 , version 1 (20-02-2020)



Théo Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, Olivier Deforges. Binary Probability Model for Learning Based Image Compression. ICASSP (International Conference on Acoustics, Speech, and Signal Processing) 2020, IEEE, May 2020, Barcelone, Spain. ⟨hal-02476067⟩
117 View
117 Download



Gmail Facebook Twitter LinkedIn More