NTIRE 2021 Challenge on Video Super-Resolution

Date Issued
2021
Author(s)
Son, S
Indian Institute of Technology Jodhpur
Lee, S
Nah, S
Timofte, R
Lee, KM
Chan, KCK
Zhou, SC
Xu, XY
Loy, CC
Jiang, BY
Lin, CM
Dong, YC
Luo, DH
Chu, WQ
Ji, XZ
Yang, SQ
Tai, Y
Wang, CJ
Li, JL
Huang, FY
Chen, CP
Chu, XJ
Zhang, J
Lu, X
Chen, LY
Lin, J
Du, GD
Hao, J
Zou, XY
Zhang, Q
Jiang, LL
Li, X
Zheng, H
Liu, FL
He, DL
Li, F
Dang, QQ
Yi, P
Wang, ZY
Jiang, K
Jiang, JJ
Ma, JY
Chen, YX
Wang, YT
Liu, T
Sun, QC
Liang, HW
Li, YM
Li, ZK
Ruan, ZB
Shang, FJ
Guo, C
Li, HN
Luo, RJ
Shen, LJ
Zafirouli, K
Karageorgos, K
Konstantoudakis, K
Dimou, A
Daras, P
Song, XW
Zhuo, X
Liu, HX
Guo, MX
Li, JL
Li, Y
Zhu, Y
Wang, Q
Zhao, SJ
Sun, XP
Zhan, G
Xie, TX
Jia, Y
Lu, YH
Zhang, WH
Sun, MD
Michelini, PN
Zhang, XH
Jiang, H
Chen, ZY
Chen, L
Xiong, ZW
Xiao, ZY
Xu, RK
Cheng, Z
Fu, XY
Song, FL
Luo, ZP
Yao, YH
Dutta, S
Shah, NA
Das, SD
Zhao, P
Shi, YK
Liu, HY
Shang, FH
Liu, YY
Chen, F
Yu, FX
Gao, RS
Bai, YX
Heo, J
Yue, SJ
Li, CH
Li, JJ
Zheng, Q
Gang, RP
Song, RX
Wee, S
Jeong, J
Li, C
Wen, GYJ
Chai, XN
Song, L
DOI
10.1109/CVPRW53098.2021.00026
Abstract
Super-Resolution (SR) is a fundamental computer vision task that aims to obtain a high-resolution clean image from the given low-resolution counterpart. This paper reviews the NTIRE 2021 Challenge on Video Super-Resolution. We present evaluation results from two competition tracks as well as the proposed solutions. Track 1 aims to develop conventional video SR methods focusing on the restoration quality. Track 2 assumes a more challenging environment with lower frame rates, casting spatio-temporal SR problem. In each competition, 247 and 223 participants have registered, respectively. During the final testing phase, 14 teams competed in each track to achieve state-of-the-art performance on video SR tasks.