Tag Archives: dataset

The Cube++ Illumination Estimation Dataset

Posted on by

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.

SDE-AWB: A Generic Solution for 2nd International Illumination Estimation Challenge (ICMV illumination estimation challenge, 2020)

Posted on by

Qian et al. proposes a neural network-based solution for three different tracks of 2nd International Illumination Estimation Challenge. They build on pre-trained Squeeze-Net backbone, differential 2D chroma histogram layer and a shallow MLP utilizing Exif information. By combining semantic feature, color feature and Exif metadata, the resulting method – SDE-AWB – obtains 1st place in both indoor and two-illuminant tracks and 2nd place in general track

The paper can be accessed here.

A New Color Constancy Dataset

Posted on by

A new color constancy paper published in CVPR2019 “When Color Constancy Goes Wrong: Correcting Improperly White-Balanced Images” by Afifi et al. has made their dataset publicly available. It contains over 65,000 pairs of incorrectly white-balanced images and their corresponding correctly white-balanced images.

Check the project page or directly access the dataset. The code is also publicly available.