Super-Resolution Based Video Coding Scheme
Abstract
In this paper, we present a super-resolution-based video coding scheme that compresses video data by combining traditional hybrid video coding and Convolutional neural network-based video coding. During video encoding, downsampling reduces the resolution of an original video in both horizontal and vertical directions to reduce original video data, and Convolutional neural networkbased super-resolution is employed after the decoding process to recover the resolution of the reconstructed video during upsampling. For core encoding and decoding processes, the latest video coding standard (i.e., VVC/H.266) is conducted. The experimental results show that the proposed method can provide efficient coding performance while maintaining good visual quality.
Cite
Text
Cho and Choi. "Super-Resolution Based Video Coding Scheme." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00190Markdown
[Cho and Choi. "Super-Resolution Based Video Coding Scheme." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/cho2022cvprw-superresolution/) doi:10.1109/CVPRW56347.2022.00190BibTeX
@inproceedings{cho2022cvprw-superresolution,
title = {{Super-Resolution Based Video Coding Scheme}},
author = {Cho, Hyun Min and Choi, Kiho},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2022},
pages = {1777-1779},
doi = {10.1109/CVPRW56347.2022.00190},
url = {https://mlanthology.org/cvprw/2022/cho2022cvprw-superresolution/}
}