3-D Context Entropy Model for Improved Practical Image Compression

Abstract

In this paper, we present our image compression framework designed for CLIC 2020 competition. Our method is based on Variational AutoEncoder (VAE) architecture which is strengthened with residual structures. In short, we make three noteworthy improvements here. First, we propose a 3-D context entropy model which can take advantage of known latent representation in current spatial locations for better entropy estimation. Second, a light-weighted residual structure is adopted for feature learning during entropy estimation. Finally, an effective training strategy is introduced for practical adaptation with different resolutions. Experiment results indicate our image compression method achieves 0.9775 MS-SSIM on CLIC validation set and 0.9809 MS-SSIM on test set.

Cite

Text

Guo et al. "3-D Context Entropy Model for Improved Practical Image Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00066

Markdown

[Guo et al. "3-D Context Entropy Model for Improved Practical Image Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/guo2020cvprw-3d/) doi:10.1109/CVPRW50498.2020.00066

BibTeX

@inproceedings{guo2020cvprw-3d,
  title     = {{3-D Context Entropy Model for Improved Practical Image Compression}},
  author    = {Guo, Zongyu and Wu, Yaojun and Feng, Runsen and Zhang, Zhizheng and Chen, Zhibo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {520-523},
  doi       = {10.1109/CVPRW50498.2020.00066},
  url       = {https://mlanthology.org/cvprw/2020/guo2020cvprw-3d/}
}