Lossy Image Compression with Normalizing Flows

TL;DR

This paper introduces a novel deep image compression method using normalizing flows, enabling high-quality reconstruction across a wide range of bit-rates and allowing consistent re-encoding without quality loss.

Contribution

It is the first to leverage normalizing flows for lossy image compression, providing invertible transformations that improve quality control and re-encoding stability.

Findings

Achieves near lossless quality at low bit-rates

Maintains consistent quality through multiple re-encodings

First application of normalizing flows in lossy image compression

Abstract

Deep learning based image compression has recently witnessed exciting progress and in some cases even managed to surpass transform coding based approaches that have been established and refined over many decades. However, state-of-the-art solutions for deep image compression typically employ autoencoders which map the input to a lower dimensional latent space and thus irreversibly discard information already before quantization. Due to that, they inherently limit the range of quality levels that can be covered. In contrast, traditional approaches in image compression allow for a larger range of quality levels. Interestingly, they employ an invertible transformation before performing the quantization step which explicitly discards information. Inspired by this, we propose a deep image compression method that is able to go from low bit-rates to near lossless quality by leveraging normalizing flows to learn a bijective mapping from the image space to a latent representation. In addition to this, we demonstrate further advantages unique to our solution, such as the ability to maintain constant quality results through re-encoding, even when performed multiple times. To the best of our knowledge, this is the first work to explore the opportunities for leveraging normalizing flows for lossy image compression.