English

NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results

Computer Vision and Pattern Recognition 2022-04-26 v2

Abstract

This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video. In this challenge, we proposed the LDV 2.0 dataset, which includes the LDV dataset (240 videos) and 95 additional videos. This challenge includes three tracks. Track 1 aims at enhancing the videos compressed by HEVC at a fixed QP. Track 2 and Track 3 target both the super-resolution and quality enhancement of HEVC compressed video. They require x2 and x4 super-resolution, respectively. The three tracks totally attract more than 600 registrations. In the test phase, 8 teams, 8 teams and 12 teams submitted the final results to Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution and quality enhancement of compressed video. The proposed LDV 2.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge (including open-sourced codes) is at https://github.com/RenYang-home/NTIRE22_VEnh_SR.

Keywords

Cite

@article{arxiv.2204.09314,
  title  = {NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results},
  author = {Ren Yang and Radu Timofte and Meisong Zheng and Qunliang Xing and Minglang Qiao and Mai Xu and Lai Jiang and Huaida Liu and Ying Chen and Youcheng Ben and Xiao Zhou and Chen Fu and Pei Cheng and Gang Yu and Junyi Li and Renlong Wu and Zhilu Zhang and Wei Shang and Zhengyao Lv and Yunjin Chen and Mingcai Zhou and Dongwei Ren and Kai Zhang and Wangmeng Zuo and Pavel Ostyakov and Vyal Dmitry and Shakarim Soltanayev and Chervontsev Sergey and Zhussip Magauiya and Xueyi Zou and Youliang Yan and Pablo Navarrete Michelini and Yunhua Lu and Diankai Zhang and Shaoli Liu and Si Gao and Biao Wu and Chengjian Zheng and Xiaofeng Zhang and Kaidi Lu and Ning Wang and Thuong Nguyen Canh and Thong Bach and Qing Wang and Xiaopeng Sun and Haoyu Ma and Shijie Zhao and Junlin Li and Liangbin Xie and Shuwei Shi and Yujiu Yang and Xintao Wang and Jinjin Gu and Chao Dong and Xiaodi Shi and Chunmei Nian and Dong Jiang and Jucai Lin and Zhihuai Xie and Mao Ye and Dengyan Luo and Liuhan Peng and Shengjie Chen and Xin Liu and Qian Wang and Xin Liu and Boyang Liang and Hang Dong and Yuhao Huang and Kai Chen and Xingbei Guo and Yujing Sun and Huilei Wu and Pengxu Wei and Yulin Huang and Junying Chen and Ik Hyun Lee and Sunder Ali Khowaja and Jiseok Yoon},
  journal= {arXiv preprint arXiv:2204.09314},
  year   = {2022}
}