CcHarmony: Color-checker based Image Harmonization Dataset

TL;DR

The paper introduces ccHarmony, a novel dataset for image harmonization created by converting foreground illumination conditions to generate realistic synthetic composite images, facilitating better training of deep harmonization networks.

Contribution

It proposes a transitive method to construct an image harmonization dataset using existing illumination data, improving over previous synthetic adjustment approaches.

Findings

The ccHarmony dataset enables more effective training of image harmonization models.

The dataset reflects natural illumination changes more accurately.

It is publicly available for research use.

Abstract

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.