Deep learning based image compression methods have achieved superior performance compared with transform based conventional codec. With end-to-end Rate-Distortion Optimization (RDO) in the codec, compression model is optimized with Lagrange multiplier λ. For conventional codec, signal is decorrelated with orthonmal transformation, and uniform quantizer is introduced. We propose a variable rate image compression method with dead-zone quantizer. Firstly, the autoencoder network is trained with RaDOGAGA \cite{radogaga} framework, which can make the latents isometric to the metric space, such as SSIM and MSE. Then the conventional dead-zone quantization method with arbitrary step size is used in the common trained network to provide the flexible rate control. With dead-zone quantizer, the experimental results show that our method performs comparably with independently optimized models within a wide range of bitrate.
@article{arxiv.2004.05855,
title = {Variable Rate Image Compression Method with Dead-zone Quantizer},
author = {Jing Zhou and Akira Nakagawa and Keizo Kato and Sihan Wen and Kimihiko Kazui and Zhiming Tan},
journal= {arXiv preprint arXiv:2004.05855},
year = {2020}
}