Learned Scalable Image Compression with Bidirectional Context Disentanglement Network

international conference on multimedia and expo, 2019.

Cited by: 7|Views22
EI

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 transfo...More

Code:

Data:

Your rating :
0

 

Tags
Comments