Paired Low-light and Normal-light Images
收藏arXiv2025-09-30 收录
下载链接:
https://github.com/ZiJun0819/VLM-Contract-Theory
下载链接
链接失效反馈官方服务:
资源简介:
该数据集包含了用于训练和验证基于扩散的人工智能生成模型(AIGC)的低光照与正常光照图像的配对集合。数据集按照80%用于训练,20%用于验证的比例进行划分,并且在验证集中随机抽取AIGC任务。该数据集规模为526对图像,其中80%用于训练,20%用于验证,任务内容涉及人工智能生成任务的分配与难度评估。
This dataset contains paired low-light and normal-light images for training and validating diffusion-based AI-generated content (AIGC) models. The dataset is split into an 80% training subset and a 20% validation subset, with AIGC tasks randomly sampled within the validation set. In total, this dataset includes 526 image pairs, 80% of which are allocated for training and 20% for validation, and the associated tasks involve the allocation and difficulty assessment of AI-generated content tasks.
提供机构:
Unity



