The NTIRE 2024 challenge on night photography rendering aimed to develop solutions for processing raw camera images taken in low-light conditions to produce high-quality RGB images. Unlike previous years, the challenge used mobile phone-captured images and evaluated both the quality and efficiency of algorithms. Participants were asked to assess the visual quality of their solutions, with the top five solutions ranked by evaluation time. The challenge included a variety of tasks, such as handling high noise levels, color vignetting, and computational constraints. The evaluation used mean opinion scores from Yandex Tasks users, who ranked pairs of images based on visual appeal. The challenge also included a baseline pipeline for in-camera rendering and provided datasets for training and testing. The winning solution in the efficiency challenge was the fastest, while the top solution in quality was the best in terms of visual appeal. The challenge attracted teams from various institutions, and the results highlighted the effectiveness of deep learning techniques in improving image quality and processing speed. The challenge also emphasized the importance of balancing quality and efficiency in image processing for night photography.The NTIRE 2024 challenge on night photography rendering aimed to develop solutions for processing raw camera images taken in low-light conditions to produce high-quality RGB images. Unlike previous years, the challenge used mobile phone-captured images and evaluated both the quality and efficiency of algorithms. Participants were asked to assess the visual quality of their solutions, with the top five solutions ranked by evaluation time. The challenge included a variety of tasks, such as handling high noise levels, color vignetting, and computational constraints. The evaluation used mean opinion scores from Yandex Tasks users, who ranked pairs of images based on visual appeal. The challenge also included a baseline pipeline for in-camera rendering and provided datasets for training and testing. The winning solution in the efficiency challenge was the fastest, while the top solution in quality was the best in terms of visual appeal. The challenge attracted teams from various institutions, and the results highlighted the effectiveness of deep learning techniques in improving image quality and processing speed. The challenge also emphasized the importance of balancing quality and efficiency in image processing for night photography.