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

• Published in: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) pp. 1220 - 1237
• Main Authors: Yang, Ren, Timofte, Radu, Zheng, Meisong, Xing, Qunliang, Qiao, Minglang, Xu, Mai, Jiang, Lai, Liu, Huaida, Chen, Ying, Ben, Youcheng, Zhou, Xiao, Fu, Chen, Cheng, Pei, Yu, Gang, Li, Junyi, Wu, Renlong, Zhang, Zhilu, Shang, Wei, Lv, Zhengyao, Chen, Yunjin, Zhou, Mingcai, Ren, Dongwei, Zhang, Kai, Zuo, Wangmeng, Ostyakov, Pavel, Dmitry, Vyal, Soltanayev, Shakarim, Sergey, Chervontsev, Magauiya, Zhussip, Zou, Xueyi, Yan, Youliang, Michelini, Pablo Navarrete, Lu, Yunhua, Zhang, Diankai, Liu, Shaoli, Gao, Si, Wu, Biao, Zheng, Chengjian, Zhang, Xiaofeng, Lu, Kaidi, Wang, Ning, Canh, Thuong Nguyen, Bach, Thong, Wang, Qing, Sun, Xiaopeng, Ma, Haoyu, Zhao, Shijie, Li, Junlin, Xie, Liangbin, Shi, Shuwei, Yang, Yujiu, Wang, Xintao, Gu, Jinjin, Dong, Chao, Shi, Xiaodi, Nian, Chunmei, Jiang, Dong, Lin, Jucai, Xie, Zhihuai, Ye, Mao, Luo, Dengyan, Peng, Liuhan, Chen, Shengjie, Liu, Xin, Wang, Qian, Liang, Boyang, Dong, Hang, Huang, Yuhao, Chen, Kai, Guo, Xingbei, Sun, Yujing, Wu, Huilei, Wei, Pengxu, Huang, Yulin, Chen, Junying, Hyun Lee, Ik, Ali Khowaja, Sunder, Yoon, Jiseok
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2022
• Subjects: Codes; Computer vision; Conferences; Pattern recognition; Superresolution; Target tracking
• ISSN: 2160-7516
• DOI: 10.1109/CVPRW56347.2022.00129

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.