NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results

Yingqian Wang, Zhengyu Liang, Fengyuan Zhang, Lvli Tian, Longguang Wang, Juncheng Li, Jungang Yang, Radu Timofte, Yulan Guo, Kai Jin, Zeqiang Wei, Angulia Yang, Di Wu, Mingzhi Gao, Xiuzhuang Zhou, Yue Yan, Yuaho Wang, Shuang Chen, Zeping Tian, Yizhi Hu, Yao Lu, Haosong Liu, Xiancheng Zhu, Huanqiang Zeng, Jianqing Zhu, Yifan Shi, Junhui Hou, Mingyang Yu, Zhijian Wu, Dingjiang Huang, Wenli Zheng, Zekai Xu, Huiyuan Fu, Heng Zhang, Zhijuan Huang, Hongyuan Yu, Zeke Zexi Hu, Haodong Chen, Vera Yuk Ying Chung, Xiaoming Chen, Zean Chen, Yeyao Chen, Gangyi Jiang, Haiyong Xu, Ting Luo, Guanglong Liao, Danhao Zhang, Siyu Zhang, Wendong Mao, Zhongfeng Wang, Sunita Arya, Abhishek Kumar Sinha, S Manthira Moorthi, Hao Zhang, Hao Sheng, Da Yang, Zhenglong Cui, Shuai Wang, Haotian Zhang, Xingzheng Wang, Yuanbo Huang, Jiahao Lin, Yuhang Lin, Ahmed Salem, Ebrahem Elkady, Hatem Ibrahem, Jae-Won Suh, Hyun-Soo Kang, Changguang Wu, Hao Hou, Pengpeng Li, Peng Huang, Jiangxin Dong, Jinhui Tang; Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops, 2025, pp. 1227-1246

Abstract

This report summarizes the 3rd NTIRE challenge on light field (LF) image super-resolution (SR), focusing on novel methods and their outcomes. This challenge aims to super-resolve LF images degraded by bicubic downsampling, and comprises three tracks: a classical track, an efficiency track, and a large model track. In total, 308 participants registered, and 13 teams submitted results that outperformed the baseline methods. The challenge has established a new state-of-the-art in LF image SR, e.g., the winning method in Track 1 achieves a 0.36 dB PSNR improvement over last year's champion on the test set. We present the submitted solutions, analyze their common trends, and highlight practical techniques. We hope this challenge will inspire further advancements in LF image SR.

Related Material

[pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_CVPR, author = {Wang, Yingqian and Liang, Zhengyu and Zhang, Fengyuan and Tian, Lvli and Wang, Longguang and Li, Juncheng and Yang, Jungang and Timofte, Radu and Guo, Yulan and Jin, Kai and Wei, Zeqiang and Yang, Angulia and Wu, Di and Gao, Mingzhi and Zhou, Xiuzhuang and Yan, Yue and Wang, Yuaho and Chen, Shuang and Tian, Zeping and Hu, Yizhi and Lu, Yao and Liu, Haosong and Zhu, Xiancheng and Zeng, Huanqiang and Zhu, Jianqing and Shi, Yifan and Hou, Junhui and Yu, Mingyang and Wu, Zhijian and Huang, Dingjiang and Zheng, Wenli and Xu, Zekai and Fu, Huiyuan and Zhang, Heng and Huang, Zhijuan and Yu, Hongyuan and Hu, Zeke Zexi and Chen, Haodong and Chung, Vera Yuk Ying and Chen, Xiaoming and Chen, Zean and Chen, Yeyao and Jiang, Gangyi and Xu, Haiyong and Luo, Ting and Liao, Guanglong and Zhang, Danhao and Zhang, Siyu and Mao, Wendong and Wang, Zhongfeng and Arya, Sunita and Sinha, Abhishek Kumar and Moorthi, S Manthira and Zhang, Hao and Sheng, Hao and Yang, Da and Cui, Zhenglong and Wang, Shuai and Zhang, Haotian and Wang, Xingzheng and Huang, Yuanbo and Lin, Jiahao and Lin, Yuhang and Salem, Ahmed and Elkady, Ebrahem and Ibrahem, Hatem and Suh, Jae-Won and Kang, Hyun-Soo and Wu, Changguang and Hou, Hao and Li, Pengpeng and Huang, Peng and Dong, Jiangxin and Tang, Jinhui}, title = {NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1227-1246} }