Learned Compression Artifact Removal by Deep Residual Networks
Abstract
We propose a method for learned compression artifact removal by post-processing of BPG compressed images. We trained three networks of different sizes. We encoded input images using BPG with different QP values. We submitted the best combination of test images, encoded with different QP and post-processed by one of three networks, which satisfy the file size and decode time constraints imposed by the Challenge. The selection of the best combination is posed as an integer programming problem. Although the visual improvements in image quality is impressive, the average PSNR improvement for the results is about 0.5 dB.
Cite
Text
Kirmemis et al. "Learned Compression Artifact Removal by Deep Residual Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.Markdown
[Kirmemis et al. "Learned Compression Artifact Removal by Deep Residual Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/kirmemis2018cvprw-learned/)BibTeX
@inproceedings{kirmemis2018cvprw-learned,
title = {{Learned Compression Artifact Removal by Deep Residual Networks}},
author = {Kirmemis, Ogun and Bakar, Gonca and Tekalp, A. Murat},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2018},
pages = {2602-2605},
url = {https://mlanthology.org/cvprw/2018/kirmemis2018cvprw-learned/}
}