NTIRE 2025 Challenge on Night Photography Rendering
Egor Ershov, S.A. Korchagin, Anatolii Khalin, Artyom Panshin, Arseniy Terekhin, Ekaterina Zaychenkova, Georgiy Lobarev, Vsevolod Plokhotnyuk, Denis Abramov, Elisey Zhdanov, Sofia Dorogova, Yasin Mamedov, Nikola Banić, Georgii Perevozchikov, Radu Timofte, Lize Zhang, Yuqian Zhang, Shuai Liu, Chaoyu Feng, Luyang Wang, Yibin Huang, Guangqi Shao, Xiaotao Wang, Lei Lei, Sishun Pan, Zhiqiang Zhong, Yang Yang, Anas M. Ali, Hamad Aloqayli, Bilel Benjdira, Wadii Boulila, Xiaoyang Ma, Zijun Gao, Leyi Xing, Zhiwei He, Yushen Zuo, Zhe Xiao, Kin-Chung Chan, Hanmin Li, Jun Xiao, Kin‐Man Lam, Yuhan Wu, Daniil Storonkin, Dmitriy Manzhura, Weixin Guo, Kele Xu, Qisheng Xu, Zijian Gao, Tianjiao Wan, Buda Vampilov, Furkan Kιnlι, Furkan Kιraç
Abstract
This paper presents a review of the NTIRE 2025 challenge on night photography rendering. The goal of the challenge was to find solutions that process raw smartphone images taken in nighttime conditions, producing output images that replicate the pipeline of a professional camera. Unlike the previous year's competition, this year a unique imaging setup was introduced: each scene was captured both by a smartphone and a professional camera with the help of a beam-splitter cube. There were two nominations: best objective quality and mean opinion score-based quality (see Fig. 1). terms of output quality were sorted by evaluation time (see Fig. 1). The solutions of the top 7 ranking participants outperformed the state-of-the-art solution in the low light enhancement field, RetinexFormer, according to objective rankings. More results can be found at https://nightimaging.org.