Variable Rate Image Compression Method with Dead-zone Quantizer

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 $\lambda$. 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.

References in corpus (4)

• Variational image compression with a scale hyperprior
• Joint Autoregressive and Hierarchical Priors for Learned Image Compression
• Lossy Image Compression with Compressive Autoencoders
• Self-reducible with easy decision version counting problems admit additive error approximation. Connections to counting complexity, exponential time complexity, and circuit lower bounds