CcHarmony: Color-checker based Image Harmonization Dataset
This addresses the data scarcity problem for researchers in computer vision, though it is incremental as it builds on existing datasets with recorded illumination.
The authors tackled the lack of training data for image harmonization by creating a new dataset called ccHarmony, which uses color-checker based illumination adjustments to generate synthetic composite images, resulting in a publicly available dataset with 74,500 image pairs.
Image harmonization targets at adjusting the foreground in a composite image to make it compatible with the background, producing a more realistic and harmonious image. Training deep image harmonization network requires abundant training data, but it is extremely difficult to acquire training pairs of composite images and ground-truth harmonious images. Therefore, existing works turn to adjust the foreground appearance in a real image to create a synthetic composite image. However, such adjustment may not faithfully reflect the natural illumination change of foreground. In this work, we explore a novel transitive way to construct image harmonization dataset. Specifically, based on the existing datasets with recorded illumination information, we first convert the foreground in a real image to the standard illumination condition, and then convert it to another illumination condition, which is combined with the original background to form a synthetic composite image. In this manner, we construct an image harmonization dataset called ccHarmony, which is named after color checker (cc). The dataset is available at https://github.com/bcmi/Image-Harmonization-Dataset-ccHarmony.