arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1812.09443cs.MM
收藏

基于双向上下文解纠缠网络的学习可分级图像压缩

Learned Scalable Image Compression with Bidirectional Context Disentanglement Network

Zhizheng Zhang, Zhibo Chen, Jianxin Lin, Weiping Li

摘要:

本文提出了一种基于深度神经网络(DNN)的学习可伸缩/渐进式图像压缩方案,称为双向上下文解纠缠网络(BCD-Net)。为了学习层次表示,我们首先采用位平面分解来粗分解信息,然后进行基于深度学习的变换。然而,不同的位平面所携带的信息不仅在熵上是不相等的,而且对于重建的重要性也不同。因此,我们采取隐藏的功能对应于不同的位平面的上下文和设计一个网络拓扑结构的双向流动,以解开上下文信息更有效的压缩表示。我们提出的方案,使我们能够获得压缩码的可分级率通过一个通过编码解码。实验结果表明,我们提出的模型优于最先进的基于DNN的可伸缩图像压缩方法的PSNR和MS-SSIM指标。此外,我们提出的模型实现了更高的性能,在MS-SSIM度量比传统的可伸缩图像编解码器。我们的技术组件的有效性也通过充分的消融实验进行了验证。

英文摘要:

In this paper, we propose a learned scalable/progressive image compression scheme based on deep neural networks (DNN), named Bidirectional Context Disentanglement Network (BCD-Net). For learning hierarchical representations, we first adopt bit-plane decomposition to decompose the information coarsely before the deep-learning-based transformation. However, the information carried by different bit-planes is not only unequal in entropy but also of different importance for reconstruction. We thus take the hidden features corresponding to different bit-planes as the context and design a network topology with bidirectional flows to disentangle the contextual information for more effective compressed representations. Our proposed scheme enables us to obtain the compressed codes with scalable rates via a one-pass encoding-decoding. Experiment results demonstrate that our proposed model outperforms the state-of-the-art DNN-based scalable image compression methods in both PSNR and MS-SSIM metrics. In addition, our proposed model achieves higher performance in MS-SSIM metric than conventional scalable image codecs. Effectiveness of our technical components is also verified through sufficient ablation experiments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑