Context-adaptive Entropy Model for End-to-end Optimized Image Compression

TL;DR

This paper introduces a novel context-adaptive entropy model for end-to-end image compression that improves distribution estimation and outperforms traditional codecs and previous neural network methods in quality metrics.

Contribution

The paper presents a new entropy model that adaptively uses bit-consuming and bit-free contexts to enhance distribution estimation in neural image compression.

Findings

Outperforms BPG and JPEG2000 in PSNR and MS-SSIM

Uses context-adaptive modeling for better compression efficiency

Achieves higher quality at similar bit rates

Abstract

We propose a context-adaptive entropy model for use in end-to-end optimized image compression. Our model exploits two types of contexts, bit-consuming contexts and bit-free contexts, distinguished based upon whether additional bit allocation is required. Based on these contexts, we allow the model to more accurately estimate the distribution of each latent representation with a more generalized form of the approximation models, which accordingly leads to an enhanced compression performance. Based on the experimental results, the proposed method outperforms the traditional image codecs, such as BPG and JPEG2000, as well as other previous artificial-neural-network (ANN) based approaches, in terms of the peak signal-to-noise ratio (PSNR) and multi-scale structural similarity (MS-SSIM) index.