Super-Resolution Based Video Coding Scheme

Hyun min Cho, Kiho Choi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 1778-1780

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 network-based 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.

Related Material

[pdf]
[bibtex]
@InProceedings{Cho_2022_CVPR, author = {Cho, Hyun min and Choi, Kiho}, title = {Super-Resolution Based Video Coding Scheme}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {1778-1780} }