okhater/lolv2-synthetic

这是一个合成的低光照数据集，包含900张训练图像和100张测试图像，专门用于低光照图像增强任务。数据集通过模拟低光照条件下的高质量图像来生成，包括调整亮度对比度、引入噪声以及保持细节等步骤，以确保生成的地面真实图像能够有效用于训练增强算法。数据集分为训练和测试两个目录，每个目录下都有地面真实图像和合成低光照输入的子目录。

This is a synthetic low-light dataset consisting of 900 training images and 100 testing images designed for low-light image enhancement tasks. The dataset is generated by simulating low-light conditions on high-quality images, including steps such as adjusting brightness and contrast, introducing noise, and preserving details to ensure that the ground truth images can be effectively used for training enhancement algorithms. The dataset is organized into separate directories for training and testing, each with subfolders for ground truth images and synthetic low-light input images.