Joint Autoregressive and Hierarchical Priors for Learned Image Compression

09/08/2018
by   David Minnen, et al.
6

Recent models for learned image compression are based on autoencoders, learning approximately invertible mappings from pixels to a quantized latent representation. These are combined with an entropy model, a prior on the latent representation that can be used with standard arithmetic coding algorithms to yield a compressed bitstream. Recently, hierarchical entropy models have been introduced as a way to exploit more structure in the latents than simple fully factorized priors, improving compression performance while maintaining end-to-end optimization. Inspired by the success of autoregressive priors in probabilistic generative models, we examine autoregressive, hierarchical, as well as combined priors as alternatives, weighing their costs and benefits in the context of image compression. While it is well known that autoregressive models come with a significant computational penalty, we find that in terms of compression performance, autoregressive and hierarchical priors are complementary and, together, exploit the probabilistic structure in the latents better than all previous learned models. The combined model yields state-of-the-art rate--distortion performance, providing a 15.8 reduction in file size over the previous state-of-the-art method based on deep learning, which corresponds to a 59.8 reduction compared to WebP and JPEG2000, and bitstreams 8.4 the current state-of-the-art image codec. To the best of our knowledge, our model is the first learning-based method to outperform BPG on both PSNR and MS-SSIM distortion metrics.

READ FULL TEXT

page 6

page 8

page 15

page 16

page 17

page 18

page 19

research
07/28/2021

Insights from Generative Modeling for Neural Video Compression

While recent machine learning research has revealed connections between ...
research
03/04/2021

A Cross Channel Context Model for Latents in Deep Image Compression

This paper presents a cross channel context model for latents in deep im...
research
11/30/2018

Practical Full Resolution Learned Lossless Image Compression

We propose the first practical learned lossless image compression system...
research
02/24/2020

Generalized Octave Convolutions for Learned Multi-Frequency Image Compression

Learned image compression has recently shown the potential to outperform...
research
08/14/2019

Video Compression With Rate-Distortion Autoencoders

In this paper we present a a deep generative model for lossy video compr...
research
09/04/2021

On the Out-of-distribution Generalization of Probabilistic Image Modelling

Out-of-distribution (OOD) detection and lossless compression constitute ...
research
01/26/2023

Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models

Lossy image compression aims to represent images in as few bits as possi...

Please sign up or login with your details

Forgot password? Click here to reset