Wide-Activated Deep Residual Networks Based Restoration for BPG-Compressed Images
Abstract
We investigate a simple pipeline to achieve high-quality image compression under very low bit-rate. The pipeline is a stack of BPG image compression and deep network based restoration. Wide-activated deep residual networks from recent advances in image super-resolution are adopted for image restoration. Experiments demonstrate that the pipeline significantly reduces the quantity loss and remove visual artifacts for compressed images.
Cite
Text
Fan et al. "Wide-Activated Deep Residual Networks Based Restoration for BPG-Compressed Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.Markdown
[Fan et al. "Wide-Activated Deep Residual Networks Based Restoration for BPG-Compressed Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/fan2018cvprw-wideactivated/)BibTeX
@inproceedings{fan2018cvprw-wideactivated,
title = {{Wide-Activated Deep Residual Networks Based Restoration for BPG-Compressed Images}},
author = {Fan, Yuchen and Yu, Jiahui and Huang, Thomas S.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2018},
pages = {2621-2624},
url = {https://mlanthology.org/cvprw/2018/fan2018cvprw-wideactivated/}
}