Post-Processing Network Based on Dense Inception Attention for Video Compression
Abstract
Traditional video coding standards, such as HEVC and VVC, have achieved significant compression performance. To further improve the coding efficiency, a post-processing network is proposed to enhance the compressed frames in this paper. Specifically, the proposed network, namely DIA_Net, contains multiple inception blocks, attention mechanism and dense residual structure. The DIA_Net can efficiently extract information of multiple scale and fully exploit the extracted feature to improve image quality. In addition, the DIA_Net is integrated into the latest test model of VVC (VTM-8.0) to post-process the reconstructed frames of the decoder for better compression performance. The proposed scheme has achieved the best performance in the sense of PSNR at the similar bitrate in the validation sets of challenge on learned image compression (CLIC), which demonstrates the superiority of our approach.
Cite
Text
Tao et al. "Post-Processing Network Based on Dense Inception Attention for Video Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00072Markdown
[Tao et al. "Post-Processing Network Based on Dense Inception Attention for Video Compression." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/tao2020cvprw-postprocessing/) doi:10.1109/CVPRW50498.2020.00072BibTeX
@inproceedings{tao2020cvprw-postprocessing,
title = {{Post-Processing Network Based on Dense Inception Attention for Video Compression}},
author = {Tao, Hao and Qian, Jian and Yu, Li and Wang, Hongkui and Zhang, Wenhao and Li, Zhengang and Wang, Ning and Zeng, Xing},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {547-551},
doi = {10.1109/CVPRW50498.2020.00072},
url = {https://mlanthology.org/cvprw/2020/tao2020cvprw-postprocessing/}
}