Ershov et al. proposes the Cube++ Illumination Dataset. Cube++ is an illumination estimation dataset that continues on the Cube+ dataset. It includes 4890 images of different scenes with known illumination colors as well as with additional semantic data that can further make the learning process more accurate. Due
to the usage of the SpyderCube color target, for every image there are two ground-truth illumination records covering different directions. Cube++ was specifically designed to tackle issues that are present in some other datasets such as too few images, inappropriate image quality, lack of scene diversity, absence of version tracking, violation of various assumptions, GDPR regulation violation, lack of additional shooting procedure info, etc. The rich content and illumination variety has been achieved by including images taken in Austria, Croatia, Czechia, Georgia, Germany, Romania, Russia, Slovenia, Turkey, and Ukraine.
You can find the paper here and the dataset download link here.