Efficient Variable Rate Image Compression With Multi-Scale Decomposition Network

作     者：Cai, Chunlei Chen, Li Zhang, Xiaoyun Gao, Zhiyong 

作者机构：Shanghai Jiao Tong Univ Dept Elect Engn Inst Image Commun & Network Engn Shanghai 200240 Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY》 (IEEE Trans Circuits Syst Video Technol)

年 卷 期：2019年第29卷第12期

页      面：3687-3700页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 

基　　金：Natural Science Foundation of Shanghai [18ZR1418100] National Natural Science Foundation of China [61771306, 61527804] Shanghai Key Laboratory of Digital Media Processing and Transmissions [STCSM18DZ2270700] 

主　　题：Image coding Resource management Transforms Transform coding Codecs Laplace equations Standards Lossy image compression multi-scale decomposition transform content adaptive rate allocation variable rate image compression convolutional neural network 

摘      要：While deep learning image compression methods have shown an impressive coding performance, most of them output a single-optimized-compression rate using a trained-specific network. However, in practice, it is essential to support the variable rate compression or meet a target rate with a high-coding performance. This paper proposes a novel image compression method, making it possible for a single convolutional neural network (CNN) model to generate the variable rate efficiently with an optimized rate-distortion (RD) performance. The method consists of CNN-based multi-scale decomposition transform and content adaptive rate allocation. Specifically, the transform network is learned to decompose the input image into several scales of representations while optimizing the RD performance for all scales. Rate allocation algorithms for two typical scenarios are provided to determine the optimal scale of each image block for a given target rate or quality factor. For a target rate, the allocation is adaptive based on content complexity. In addition, for a target quality factor which indicates a tradeoff between the rate and the quality, the optimal scale is determined by minimizing the RD cost. The experimental results have shown that our method has outperformed the JPEG2000 and BPG standards with high efficiency and the state-of-the-art RD performance as measured by the multi-scale structural similarity index metric. Moreover, our method can strictly control the rate to generate the target compression result.