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

Longguang Wang, Yulan Guo, Yingqian Wang, Juncheng Li, Shuhang Gu, Radu Timofte, Liangyu Chen, Xiaojie Chu, Wenqing Yu, Kai Jin, Zeqiang Wei, Sha Guo, Angulia Yang, Xiuzhuang Zhou, Guodong Guo, Bin Dai, Feiyue Peng, Huaxin Xiao, Shen Yan, Yuxiang Liu, Hanxiao Cai, Pu Cao, Yang Nie, Lu Yang, Qing Song, Xiaotao Hu, Jun Xu, Mai Xu, Junpeng Jing, Xin Deng, Qunliang Xing, Minglang Qiao, Zhenyu Guan, Wenlong Guo, Chenxu Peng, Zan Chen, Junyang Chen, Hao Li, Junbin Chen, Weijie Li, Zhijing Yang, Gen Li, Aijin Li, Lei Sun, Dafeng Zhang, Shizhuo Liu, Jiangtao Zhang, Yanyun Qu, Hao-Hsiang Yang, Zhi-Kai Huang, Wei-Ting Chen, Hua-En Chang, Sy-Yen Kuo, Qiaohui Liang, Jianxin Lin, Yijun Wang, Lianying Yin, Rongju Zhang, Wei Zhao, Peng Xiao, Rongjian Xu, Zhilu Zhang, Wangmeng Zuo, Hansheng Guo, Guangwei Gao, Tieyong Zeng, Huicheng Pi, Shunli Zhang, Joohyeok Kim, HyeonA Kim, Eunpil Park, Jae-Young Sim, Jucai Zhai, Pengcheng Zeng, Yang Liu, Chihao Ma, Yulin Huang, Junying Chen; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 906-919

Abstract

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.

Related Material

[pdf]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Longguang and Guo, Yulan and Wang, Yingqian and Li, Juncheng and Gu, Shuhang and Timofte, Radu and Chen, Liangyu and Chu, Xiaojie and Yu, Wenqing and Jin, Kai and Wei, Zeqiang and Guo, Sha and Yang, Angulia and Zhou, Xiuzhuang and Guo, Guodong and Dai, Bin and Peng, Feiyue and Xiao, Huaxin and Yan, Shen and Liu, Yuxiang and Cai, Hanxiao and Cao, Pu and Nie, Yang and Yang, Lu and Song, Qing and Hu, Xiaotao and Xu, Jun and Xu, Mai and Jing, Junpeng and Deng, Xin and Xing, Qunliang and Qiao, Minglang and Guan, Zhenyu and Guo, Wenlong and Peng, Chenxu and Chen, Zan and Chen, Junyang and Li, Hao and Chen, Junbin and Li, Weijie and Yang, Zhijing and Li, Gen and Li, Aijin and Sun, Lei and Zhang, Dafeng and Liu, Shizhuo and Zhang, Jiangtao and Qu, Yanyun and Yang, Hao-Hsiang and Huang, Zhi-Kai and Chen, Wei-Ting and Chang, Hua-En and Kuo, Sy-Yen and Liang, Qiaohui and Lin, Jianxin and Wang, Yijun and Yin, Lianying and Zhang, Rongju and Zhao, Wei and Xiao, Peng and Xu, Rongjian and Zhang, Zhilu and Zuo, Wangmeng and Guo, Hansheng and Gao, Guangwei and Zeng, Tieyong and Pi, Huicheng and Zhang, Shunli and Kim, Joohyeok and Kim, HyeonA and Park, Eunpil and Sim, Jae-Young and Zhai, Jucai and Zeng, Pengcheng and Liu, Yang and Ma, Chihao and Huang, Yulin and Chen, Junying}, title = {NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {906-919} }