ANFIC: Image Compression Using Augmented Normalizing Flows

TL;DR

ANFIC is a novel image compression method that leverages augmented normalizing flows and stacked VAEs to achieve high compression efficiency and flexible quality levels, outperforming many existing learned methods.

Contribution

This work introduces the first VAE-based flow model for image compression, enhancing compression performance through hierarchical stacking and supporting variable rates with a single model.

Findings

ANFIC achieves state-of-the-art performance in PSNR-RGB metrics.

It performs close to VVC intra coding across various compression rates.

Supports a wide range of quality levels without changing network architecture.

Abstract

This paper introduces an end-to-end learned image compression system, termed ANFIC, based on Augmented Normalizing Flows (ANF). ANF is a new type of flow model, which stacks multiple variational autoencoders (VAE) for greater model expressiveness. The VAE-based image compression has gone mainstream, showing promising compression performance. Our work presents the first attempt to leverage VAE-based compression in a flow-based framework. ANFIC advances further compression efficiency by stacking and extending hierarchically multiple VAE's. The invertibility of ANF, together with our training strategies, enables ANFIC to support a wide range of quality levels without changing the encoding and decoding networks. Extensive experimental results show that in terms of PSNR-RGB, ANFIC performs comparably to or better than the state-of-the-art learned image compression. Moreover, it performs close to VVC intra coding, from low-rate compression up to nearly-lossless compression. In particular, ANFIC achieves the state-of-the-art performance, when extended with conditional convolution for variable rate compression with a single model.