NTIRE 2024 Challenge on Night Photography Rendering

NTIRE 2024 Challenge on Night Photography Rendering

18 Jun 2024 | Egor Ershov, Artyom Panshin, Oleg Karasev, Sergey Korchagin, Shepelev Lev, Alexandr Startsev, Daniil Vladimirov, Ekaterina Zaychenkova, Nikola Banić, Dmitrii Iarchuk, Maria Efimova, Radu Timofte, Arseniy Terekhin, Shuwei Yue, Yuyang Liu, Minchen Wei, Lu Xu, Chao Zhang, Yasi Wang, Furkan Kinalı, Doğa Yılmaz, Barış Özcan, Furkan Kıraç, Shuai Liu, Jingyuan Xiao, Chaoyu Feng, Hao Wang, Guangqi Shao, Yuqian Zhang, Yibin Huang, Wei Luo, Liming Wang, Xiaotao Wang, Lei Lei, Simone Zini, Claudio Rota, Marco Buzzelli, Simone Bianco, Raimondo Schettini, Jin Guo, Tianli Liu, Mohao Wu, Ben Shao, Qirui Yang, Xianghui Li, Qihua Cheng, Huanjing Yue
This paper reviews the NTIRE 2024 challenge on night photography rendering, which aimed to find solutions that process raw camera images taken in nighttime conditions to produce photo-quality output images in the standard RGB (sRGB) space. Unlike previous years, the challenge images were collected with mobile phones, and both the quality and speed of algorithms were evaluated. The evaluation was conducted through a user study where participants assessed the visual quality of the proposed solutions. The top 5 solutions were sorted by evaluation time, with the winner being the most efficient solution. The challenge highlighted the unique challenges of nighttime photography, such as multiple illuminants and high noise levels, and emphasized the need for specialized image processing techniques. The paper also provides a detailed description of the challenge setup, results, and discussions on the obtained results, along with the affiliations of the participating teams.This paper reviews the NTIRE 2024 challenge on night photography rendering, which aimed to find solutions that process raw camera images taken in nighttime conditions to produce photo-quality output images in the standard RGB (sRGB) space. Unlike previous years, the challenge images were collected with mobile phones, and both the quality and speed of algorithms were evaluated. The evaluation was conducted through a user study where participants assessed the visual quality of the proposed solutions. The top 5 solutions were sorted by evaluation time, with the winner being the most efficient solution. The challenge highlighted the unique challenges of nighttime photography, such as multiple illuminants and high noise levels, and emphasized the need for specialized image processing techniques. The paper also provides a detailed description of the challenge setup, results, and discussions on the obtained results, along with the affiliations of the participating teams.
Reach us at info@study.space
[slides and audio] NTIRE 2024 Challenge on Night Photography Rendering