NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results

In this paper, we summarize the 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results. This challenge has 1 track aiming at the stereo image super-resolution problem under a standard bicu...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) pp. 905 - 918
Main Authors Wang, Longguang, Guo, Yulan, Wang, Yingqian, Li, Juncheng, Gu, Shuhang, Timofte, Radu, Chen, Liangyu, Chu, Xiaojie, Yu, Wenqing, Jin, Kai, Wei, Zeqiang, Guo, Sha, Yang, Angulia, Zhou, Xiuzhuang, Guo, Guodong, Dai, Bin, Peng, Feiyue, Xiao, Huaxin, Yan, Shen, Liu, Yuxiang, Cai, Hanxiao, Cao, Pu, Nie, Yang, Yang, Lu, Song, Qing, Hu, Xiaotao, Xu, Jun, Xu, Mai, Jing, Junpeng, Deng, Xin, Xing, Qunliang, Qiao, Minglang, Guan, Zhenyu, Guo, Wenlong, Peng, Chenxu, Chen, Zan, Chen, Junyang, Li, Hao, Chen, Junbin, Li, Weijie, Yang, Zhijing, Li, Gen, Li, Aijin, Sun, Lei, Zhang, Dafeng, Liu, Shizhuo, Zhang, Jiangtao, Qu, Yanyun, Yang, Hao-Hsiang, Huang, Zhi-Kai, Chen, Wei-Ting, Chang, Hua-En, Kuo, Sy-Yen, Liang, Qiaohui, Lin, Jianxin, Wang, Yijun, Yin, Lianying, Zhang, Rongju, Zhao, Wei, Xiao, Peng, Xu, Rongjian, Zhang, Zhilu, Zuo, Wangmeng, Guo, Hansheng, Gao, Guangwei, Zeng, Tieyong, Pi, Huicheng, Zhang, Shunli, Kim, Joohyeok, Kim, HyeonA, Park, Eunpil, Sim, Jae-Young, Zhai, Jucai, Zeng, Pengcheng, Liu, Yang, Ma, Chihao, Huang, Yulin, Chen, Junying
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2022
Subjects
Benchmark testing
Computer vision
Conferences
Degradation
Image restoration
Pattern recognition
Superresolution
Online AccessGet full text

Cover

More Information
Summary:In this paper, we summarize the 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results. This challenge has 1 track aiming at the stereo image super-resolution problem under a standard bicubic degradation. In total, 238 participants were successfully registered, and 21 teams competed in the final testing phase. Among those participants, 20 teams successfully submitted results with PSNR (RGB) scores better than the baseline. This challenge establishes a new benchmark for stereo image SR.
ISSN:2160-7516
DOI:10.1109/CVPRW56347.2022.00105