Litcius/Paper detail

NTIRE 2025 Challenge on Raw Image Restoration and Super-Resolution

Marcos V. Conde, Radu Timofte, Zhihong Lu, Xiang‐Yu Kong, Xiaoxia Xing, Fan Wang, Suejin Han, Minkyu Park, Tianyu Zhang, Xin Luo, Yeda Chen, Dong Liu, Li Pang, Yuhang Yang, Wáng Hóngzhōng, Xiangyong Cao, Ruixuan Jiang, Senyan Xu, Siyuan Jiang, Xueyang Fu, Zheng-Jun Zha, Tianyu Hao, Yuhong He, Ruoqi Li, Yaru Yang, Yu Xiang, Guanlan Hong, Minmin Yi, Y Chen, Liwen Zhang, Zijie Jin, Cheng Li, Lian Liu, Song Wei, Heng Sun, Yubo Wang, Jinghua Wang, Jiajie Lu, Watchara Ruangsang

202524 citationsDOI

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 <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$2 x$</tex>, 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.

Topics & Concepts

Image restorationArtificial intelligenceComputer visionComputer scienceNoise (video)Image (mathematics)Raw dataImage processingRaw materialRGB color modelAdvanced Image Processing TechniquesMedical Imaging Techniques and Applications
NTIRE 2025 Challenge on Raw Image Restoration and Super-Resolution | Litcius