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.
@article{arxiv.2107.08470,
title = {ANFIC: Image Compression Using Augmented Normalizing Flows},
author = {Yung-Han Ho and Chih-Chun Chan and Wen-Hsiao Peng and Hsueh-Ming Hang and Marek Domanski},
journal= {arXiv preprint arXiv:2107.08470},
year = {2021}
}