English

Learned Scalable Image Compression with Bidirectional Context Disentanglement Network

Multimedia 2019-04-23 v2

Abstract

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.

Keywords

Cite

@article{arxiv.1812.09443,
  title  = {Learned Scalable Image Compression with Bidirectional Context Disentanglement Network},
  author = {Zhizheng Zhang and Zhibo Chen and Jianxin Lin and Weiping Li},
  journal= {arXiv preprint arXiv:1812.09443},
  year   = {2019}
}

Comments

IEEE International Conference on Multimedia and Expo (ICME2019)

R2 v1 2026-06-23T06:54:18.758Z