NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results

Abstract

This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with focus on proposed solutions and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is de-signed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh

Cite

Text

Yang. "NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00075

Markdown

[Yang. "NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/yang2021cvprw-ntire/) doi:10.1109/CVPRW53098.2021.00075

BibTeX

@inproceedings{yang2021cvprw-ntire,
  title     = {{NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results}},
  author    = {Yang, Ren},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {647-666},
  doi       = {10.1109/CVPRW53098.2021.00075},
  url       = {https://mlanthology.org/cvprw/2021/yang2021cvprw-ntire/}
}