Learned Scalable Image Compression with Bidirectional Context Disentanglement Network
arXiv:1812.09443
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.
arXiv commentIEEE International Conference on Multimedia and Expo (ICME2019)
References in corpus (5)
- Variational image compression with a scale hyperprior
- Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
- Joint Autoregressive and Hierarchical Priors for Learned Image Compression
- Variable Rate Image Compression with Recurrent Neural Networks
- Real-Time Adaptive Image Compression