1、23arxiv_LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement中提到
LOL-v2文献来源：Sparse gradient regularized deep retinex network for robust low-light image enhancement
VE-LOL文献来源：Benchmarking low-light image enhancement and beyond.
LOL-v2： real数据集训练测试689/100已核对 syn数据集训练测试900/100，https://github.com/flyywh/CVPR-2020-Semi-Low-Light
VE-LOL-L：是成对的，里面cap数据集训练测试400/100，syn数据集900/100发现和LOL-v2上面那个链接给出的数据集是一样的
VE-LOL-H：是不成对的
---------------------------------------------------------------------------------------------------------------
大佬链接：LOL-v2数据集和VE-LOL数据集的区别_QT-Smile的博客-CSDN博客