NTIRE 2025 Challenge on Raw Image Restoration and Super-Resolution

Marcos V. Conde; Radu Timofte; Zihao Lu; Xiangyu Kong; Xiaoxia Xing; Fan Wang; Suejin Han; Min Kyu Park; Tianyu Zhang; Xin Luo; Yeda Chen; Dong Liu; Li Pang; Yuhang Yang; Hongzhong Wang; Xiangyong Cao; Ruixuan Jiang; Senyan Xu; Siyuan Jiang; Xueyang Fu; Zheng Jun Zha; Tianyu Hao; Yuhong He; Ruoqi Li; Yueqi Yang; Xiang Yu; Guanlan Hong; Minmin Yi; Yuanjia Chen; Liwen Zhang; Zijie Jin; Cheng Li; Lian Liu; Wei Song; Heng Sun; Yubo Wang; Jinghua Wang; Jiajie Lu; Watchara Ruangsang

doi:10.1109/CVPRW67362.2025.00110

NTIRE 2025 Challenge on Raw Image Restoration and Super-Resolution

Marcos V. Conde
, Radu Timofte
, Zihao Lu
, Xiangyu Kong
, Xiaoxia Xing
, Fan Wang
, Suejin Han
, Min Kyu Park
, Tianyu Zhang
, Xin Luo
, Yeda Chen
, Dong Liu
, Li Pang
, Yuhang Yang
, Hongzhong Wang
, Xiangyong Cao
, Ruixuan Jiang
, Senyan Xu
, Siyuan Jiang
, Xueyang Fu

Zheng Jun Zha, Tianyu Hao, Yuhong He, Ruoqi Li, Yueqi Yang, Xiang Yu, Guanlan Hong, Minmin Yi, Yuanjia Chen, Liwen Zhang, Zijie Jin, Cheng Li, Lian Liu, Wei Song, Heng Sun, Yubo Wang, Jinghua Wang, Jiajie Lu, Watchara Ruangsang

Faculty of Electronic and Information Engineering

University of Würzburg

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

23 Scopus citations

Abstract

This paper reviews the NTIRE 2025 RAW Image Restoration and Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Restoration and Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. The goal of this challenge is two fold, (i) restore RAW images with blur and noise degradations, (ii) upscale RAW Bayer images by 2 x, considering unknown noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. This report presents the current state-of-the-art in RAW Restoration.

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	1139-1162
Number of pages	24
ISBN (Electronic)	9798331599942
DOIs	https://doi.org/10.1109/CVPRW67362.2025.00110
State	Published - 2025
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

isp
low-level
photography
raw
restoration
sensor
super-resolution

Access to Document

10.1109/CVPRW67362.2025.00110

Cite this

Conde, M. V., Timofte, R., Lu, Z., Kong, X., Xing, X., Wang, F., Han, S., Park, M. K., Zhang, T., Luo, X., Chen, Y., Liu, D., Pang, L., Yang, Y., Wang, H., Cao, X., Jiang, R., Xu, S., Jiang, S., ... Ruangsang, W. (2025). NTIRE 2025 Challenge on Raw Image Restoration and Super-Resolution. In Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025 (pp. 1139-1162). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE Computer Society. https://doi.org/10.1109/CVPRW67362.2025.00110

@inproceedings{b0b99d61ca6d45b6bdb399ad914ace0e,

title = "NTIRE 2025 Challenge on Raw Image Restoration and Super-Resolution",

abstract = "This paper reviews the NTIRE 2025 RAW Image Restoration and Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Restoration and Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. The goal of this challenge is two fold, (i) restore RAW images with blur and noise degradations, (ii) upscale RAW Bayer images by 2 x, considering unknown noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. This report presents the current state-of-the-art in RAW Restoration.",

keywords = "isp, low-level, photography, raw, restoration, sensor, super-resolution",

author = "Conde, \{Marcos V.\} and Radu Timofte and Zihao Lu and Xiangyu Kong and Xiaoxia Xing and Fan Wang and Suejin Han and Park, \{Min Kyu\} and Tianyu Zhang and Xin Luo and Yeda Chen and Dong Liu and Li Pang and Yuhang Yang and Hongzhong Wang and Xiangyong Cao and Ruixuan Jiang and Senyan Xu and Siyuan Jiang and Xueyang Fu and Zha, \{Zheng Jun\} and Tianyu Hao and Yuhong He and Ruoqi Li and Yueqi Yang and Xiang Yu and Guanlan Hong and Minmin Yi and Yuanjia Chen and Liwen Zhang and Zijie Jin and Cheng Li and Lian Liu and Wei Song and Heng Sun and Yubo Wang and Jinghua Wang and Jiajie Lu and Watchara Ruangsang",

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/CVPRW67362.2025.00110",

language = "英语",

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

publisher = "IEEE Computer Society",

pages = "1139--1162",

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

}

Conde, MV, Timofte, R, Lu, Z, Kong, X, Xing, X, Wang, F, Han, S, Park, MK, Zhang, T, Luo, X, Chen, Y, Liu, D, Pang, L, Yang, Y, Wang, H, Cao, X, Jiang, R, Xu, S, Jiang, S, Fu, X, Zha, ZJ, Hao, T, He, Y, Li, R, Yang, Y, Yu, X, Hong, G, Yi, M, Chen, Y, Zhang, L, Jin, Z, Li, C, Liu, L, Song, W, Sun, H, Wang, Y, Wang, J, Lu, J & Ruangsang, W 2025, NTIRE 2025 Challenge on Raw Image Restoration and Super-Resolution. 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. 1139-1162, 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025, Nashville, United States, 11/06/25. https://doi.org/10.1109/CVPRW67362.2025.00110

NTIRE 2025 Challenge on Raw Image Restoration and Super-Resolution. / Conde, Marcos V.; Timofte, Radu; Lu, Zihao et al.
Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society, 2025. p. 1139-1162 (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 Raw Image Restoration and Super-Resolution

AU - Conde, Marcos V.

AU - Timofte, Radu

AU - Lu, Zihao

AU - Kong, Xiangyu

AU - Xing, Xiaoxia

AU - Wang, Fan

AU - Han, Suejin

AU - Park, Min Kyu

AU - Zhang, Tianyu

AU - Luo, Xin

AU - Chen, Yeda

AU - Liu, Dong

AU - Pang, Li

AU - Yang, Yuhang

AU - Wang, Hongzhong

AU - Cao, Xiangyong

AU - Jiang, Ruixuan

AU - Xu, Senyan

AU - Jiang, Siyuan

AU - Fu, Xueyang

AU - Zha, Zheng Jun

AU - Hao, Tianyu

AU - He, Yuhong

AU - Li, Ruoqi

AU - Yang, Yueqi

AU - Yu, Xiang

AU - Hong, Guanlan

AU - Yi, Minmin

AU - Chen, Yuanjia

AU - Zhang, Liwen

AU - Jin, Zijie

AU - Li, Cheng

AU - Liu, Lian

AU - Song, Wei

AU - Sun, Heng

AU - Wang, Yubo

AU - Wang, Jinghua

AU - Lu, Jiajie

AU - Ruangsang, Watchara

PY - 2025

Y1 - 2025

N2 - This paper reviews the NTIRE 2025 RAW Image Restoration and Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Restoration and Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. The goal of this challenge is two fold, (i) restore RAW images with blur and noise degradations, (ii) upscale RAW Bayer images by 2 x, considering unknown noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. This report presents the current state-of-the-art in RAW Restoration.

AB - This paper reviews the NTIRE 2025 RAW Image Restoration and Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Restoration and Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. The goal of this challenge is two fold, (i) restore RAW images with blur and noise degradations, (ii) upscale RAW Bayer images by 2 x, considering unknown noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. This report presents the current state-of-the-art in RAW Restoration.

KW - isp

KW - low-level

KW - photography

KW - raw

KW - restoration

KW - sensor

KW - super-resolution

UR - https://www.scopus.com/pages/publications/105017861580

U2 - 10.1109/CVPRW67362.2025.00110

DO - 10.1109/CVPRW67362.2025.00110

M3 - 会议稿件

AN - SCOPUS:105017861580

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

SP - 1139

EP - 1162

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

PB - IEEE Computer Society

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

Y2 - 11 June 2025 through 12 June 2025

ER -

Conde MV, Timofte R, Lu Z, Kong X, Xing X, Wang F et al. NTIRE 2025 Challenge on Raw Image Restoration and Super-Resolution. In Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society. 2025. p. 1139-1162. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW67362.2025.00110

NTIRE 2025 Challenge on Raw Image Restoration and Super-Resolution

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this