Joint Autoregressive and Hierarchical Priors for Learned Image Compression

TL;DR

This paper introduces a combined autoregressive and hierarchical prior model for learned image compression, achieving state-of-the-art rate-distortion performance and outperforming traditional codecs like BPG on multiple metrics.

Contribution

It proposes a novel combined prior approach that leverages autoregressive and hierarchical models, significantly improving compression efficiency over previous learned methods.

Findings

Achieves 15.8% average reduction in file size over previous state-of-the-art.

Outperforms BPG on both PSNR and MS-SSIM metrics.

Provides the first learning-based method surpassing BPG in image compression.

Abstract

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% average reduction in file size over the previous state-of-the-art method based on deep learning, which corresponds to a 59.8% size reduction over JPEG, more than 35% reduction compared to WebP and JPEG2000, and bitstreams 8.4% smaller than BPG, 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.