摘要： While deep learning image compression methods have shown impressive coding performance, most of them output a single optimized compression rate using a trained specific network. However, in practical it is essential to support variable rate compression or meet a target rate with high coding performance. This paper proposes a novel image compression method, making it possible for a single CNN model to generate variable rate efficiently with 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. And for a target quality-factor which indicates a trade-off between rate and quality, the optimal scale is determined by minimizing the RD cost. Experimental results have shown that our method has outperformed JPEG2000 and BPG standards with high efficiency and state-of-the-art RD performance as measured by MS-SSIM. Moreover, our method can strictly control the rate to generate the target compression result.