An extended context-based entropy hybrid modeling for image compression

作者：

Highlights：

• An Extended Context-Based Entropy Hybrid Modeling for Image Compression.

• Improved autoencoder architecture.

• Outperforms the state-of-the-art deep learning-based layered coding scheme and traditional codecs such as BPG in RGB444 space.

摘要

•An Extended Context-Based Entropy Hybrid Modeling for Image Compression.•Improved autoencoder architecture.•Outperforms the state-of-the-art deep learning-based layered coding scheme and traditional codecs such as BPG in RGB444 space.

论文关键词：Hybrid coding framework,Entropy coding,Importance map,Latent representation,Residual

论文评审过程：Received 7 August 2020, Revised 4 February 2021, Accepted 13 March 2021, Available online 26 March 2021, Version of Record 29 March 2021.

论文官网地址：https://doi.org/10.1016/j.image.2021.116244