Extended End-to-End Optimized Image Compression Method Based on a Context-Adaptive Entropy Model
Abstract
In this paper, we propose an extended compression method using a context-adaptive entropy model. Based on the Lee et al. Ju Hu approach, we extend the network structure so that compression and quality enhancement methods are jointly optimized. In terms of contexts for estimating distributions, we additionally use offset information. By exploiting the extended structure and the additional con-texts, we obtain substantially improved compression performance, in terms of multi-scale structural similarity (MS-SSIM) index, compared to the model without the extensions.
Cite
Text
Lee et al. "Extended End-to-End Optimized Image Compression Method Based on a Context-Adaptive Entropy Model." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.Markdown
[Lee et al. "Extended End-to-End Optimized Image Compression Method Based on a Context-Adaptive Entropy Model." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/lee2019cvprw-extended/)BibTeX
@inproceedings{lee2019cvprw-extended,
title = {{Extended End-to-End Optimized Image Compression Method Based on a Context-Adaptive Entropy Model}},
author = {Lee, Jooyoung and Cho, Seunghyun and Jeong, Seyoon and Kwon, Hyoungjin and Ko, Hyunsuk and Kim, Hui Yong and Choi, Jin Soo},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
url = {https://mlanthology.org/cvprw/2019/lee2019cvprw-extended/}
}