Variable Rate Image Compression Method with Dead-zone Quantizer

Jing Zhou, Akira Nakagawa, Keizo Kato, Sihan Wen, Kimihiko Kazui, Zhiming Tan

Abstract: 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 l. For conventional codec, signal is decorrelated with orthonormal 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 [6] 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.