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; Yuhao 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

doi:10.1109/CVPRW67362.2025.00116

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, Yuhao Wang, Shuang Chen, Zeping Tian, Yizhi HuYao 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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

26 Scopus citations

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.

Original language	English
Title of host publication	Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025
Publisher	IEEE Computer Society
Pages	1218-1237
Number of pages	20
ISBN (Electronic)	9798331599942
DOIs	https://doi.org/10.1109/CVPRW67362.2025.00116
State	Published - 2025
Externally published	Yes
Event	2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025 - Nashville, United States Duration: 11 Jun 2025 → 12 Jun 2025

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025
Country/Territory	United States
City	Nashville
Period	11/06/25 → 12/06/25

Keywords

challenge
light field
super-resolution

Access to Document

10.1109/CVPRW67362.2025.00116

Cite this

Wang, Y., Liang, Z., Zhang, F., Tian, L., Wang, L., Li, J., Yang, J., Timofte, R., Guo, Y., Jin, K., Wei, Z., Yang, A., Wu, D., Gao, M., Zhou, X., Yan, Y., Wang, Y., Chen, S., Tian, Z., ... Tang, J. (2025). NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results. In Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025 (pp. 1218-1237). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE Computer Society. https://doi.org/10.1109/CVPRW67362.2025.00116

Wang, Yingqian ; Liang, Zhengyu ; Zhang, Fengyuan et al. / NTIRE 2025 Challenge on Light Field Image Super-Resolution : Methods and Results. Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society, 2025. pp. 1218-1237 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

@inproceedings{470e20c3140641d8802a7e5d69d73de1,

title = "NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results",

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.",

keywords = "challenge, light field, super-resolution",

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

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025 ; Conference date: 11-06-2025 Through 12-06-2025",

year = "2025",

doi = "10.1109/CVPRW67362.2025.00116",

language = "英语",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "1218--1237",

booktitle = "Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025",

address = "美国",

}

Wang, Y, Liang, Z, Zhang, F, Tian, L, Wang, L, Li, J, Yang, J, Timofte, R, Guo, Y, Jin, K, Wei, Z, Yang, A, Wu, D, Gao, M, Zhou, X, Yan, Y, Wang, Y, Chen, S, Tian, Z, Hu, Y, Lu, Y, Liu, H, Zhu, X, Zeng, H, Zhu, J, Shi, Y, Hou, J, Yu, M, Wu, Z, Huang, D, Zheng, W, Xu, Z, Fu, H, Zhang, H, Huang, Z, Yu, H, Hu, ZZ, Chen, H, Chung, VYY, Chen, X, Chen, Z, Chen, Y, Jiang, G, Xu, H, Luo, T, Liao, G, Zhang, D, Zhang, S, Mao, W, Wang, Z, Arya, S, Sinha, AK, Moorthi, SM, Zhang, H, Sheng, H, Yang, D, Cui, Z, Wang, S, Zhang, H, Wang, X, Huang, Y, Lin, J, Lin, Y, Salem, A, Elkady, E, Ibrahem, H, Suh, JW, Kang, HS, Wu, C, Hou, H, Li, P, Huang, P, Dong, J & Tang, J 2025, NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results. in Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE Computer Society, pp. 1218-1237, 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025, Nashville, United States, 11/06/25. https://doi.org/10.1109/CVPRW67362.2025.00116

NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results. / Wang, Yingqian; Liang, Zhengyu; Zhang, Fengyuan et al.
Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society, 2025. p. 1218-1237 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - NTIRE 2025 Challenge on Light Field Image Super-Resolution

T2 - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025

AU - Wang, Yingqian

AU - Liang, Zhengyu

AU - Zhang, Fengyuan

AU - Tian, Lvli

AU - Wang, Longguang

AU - Li, Juncheng

AU - Yang, Jungang

AU - Timofte, Radu

AU - Guo, Yulan

AU - Jin, Kai

AU - Wei, Zeqiang

AU - Yang, Angulia

AU - Wu, Di

AU - Gao, Mingzhi

AU - Zhou, Xiuzhuang

AU - Yan, Yue

AU - Wang, Yuhao

AU - Chen, Shuang

AU - Tian, Zeping

AU - Hu, Yizhi

AU - Lu, Yao

AU - Liu, Haosong

AU - Zhu, Xiancheng

AU - Zeng, Huanqiang

AU - Zhu, Jianqing

AU - Shi, Yifan

AU - Hou, Junhui

AU - Yu, Mingyang

AU - Wu, Zhijian

AU - Huang, Dingjiang

AU - Zheng, Wenli

AU - Xu, Zekai

AU - Fu, Huiyuan

AU - Zhang, Heng

AU - Huang, Zhijuan

AU - Yu, Hongyuan

AU - Hu, Zeke Zexi

AU - Chen, Haodong

AU - Chung, Vera Yuk Ying

AU - Chen, Xiaoming

AU - Chen, Zean

AU - Chen, Yeyao

AU - Jiang, Gangyi

AU - Xu, Haiyong

AU - Luo, Ting

AU - Liao, Guanglong

AU - Zhang, Danhao

AU - Zhang, Siyu

AU - Mao, Wendong

AU - Wang, Zhongfeng

AU - Arya, Sunita

AU - Sinha, Abhishek Kumar

AU - Moorthi, S. Manthira

AU - Zhang, Hao

AU - Sheng, Hao

AU - Yang, Da

AU - Cui, Zhenglong

AU - Wang, Shuai

AU - Zhang, Haotian

AU - Wang, Xingzheng

AU - Huang, Yuanbo

AU - Lin, Jiahao

AU - Lin, Yuhang

AU - Salem, Ahmed

AU - Elkady, Ebrahem

AU - Ibrahem, Hatem

AU - Suh, Jae Won

AU - Kang, Hyun Soo

AU - Wu, Changguang

AU - Hou, Hao

AU - Li, Pengpeng

AU - Huang, Peng

AU - Dong, Jiangxin

AU - Tang, Jinhui

PY - 2025

Y1 - 2025

N2 - 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.

AB - 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.

KW - challenge

KW - light field

KW - super-resolution

UR - https://www.scopus.com/pages/publications/105017857361

U2 - 10.1109/CVPRW67362.2025.00116

DO - 10.1109/CVPRW67362.2025.00116

M3 - 会议稿件

AN - SCOPUS:105017857361

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 1218

EP - 1237

BT - Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025

PB - IEEE Computer Society

Y2 - 11 June 2025 through 12 June 2025

ER -

Wang Y, Liang Z, Zhang F, Tian L, Wang L, Li J et al. NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results. In Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society. 2025. p. 1218-1237. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW67362.2025.00116

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

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this