Real-Time Adaptive Image Compression

TL;DR

This paper introduces a real-time, machine learning-based image compression method that significantly outperforms traditional codecs in size reduction while maintaining fast processing speeds and visually pleasing results.

Contribution

It presents a novel autoencoder architecture with adaptive coding and adversarial training, achieving superior compression ratios and real-time performance.

Findings

Produces images 2.5x smaller than JPEG and JPEG 2000

Encodes/decodes in around 10ms per image on GPU

Generates visually pleasing reconstructions at low bitrates

Abstract

We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time. Our algorithm typically produces files 2.5 times smaller than JPEG and JPEG 2000, 2 times smaller than WebP, and 1.7 times smaller than BPG on datasets of generic images across all quality levels. At the same time, our codec is designed to be lightweight and deployable: for example, it can encode or decode the Kodak dataset in around 10ms per image on GPU. Our architecture is an autoencoder featuring pyramidal analysis, an adaptive coding module, and regularization of the expected codelength. We also supplement our approach with adversarial training specialized towards use in a compression setting: this enables us to produce visually pleasing reconstructions for very low bitrates.