Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation
This work addresses image harmonization for computer vision applications, offering incremental improvements over existing methods.
The paper tackles the problem of image harmonization by adjusting foreground illumination to match the background, achieving significant improvement through globally guided feature transformation and relation distillation, with experiments on iHarmony4 and a new ccHarmony dataset.
Given a composite image, image harmonization aims to adjust the foreground illumination to be consistent with background. Previous methods have explored transforming foreground features to achieve competitive performance. In this work, we show that using global information to guide foreground feature transformation could achieve significant improvement. Besides, we propose to transfer the foreground-background relation from real images to composite images, which can provide intermediate supervision for the transformed encoder features. Additionally, considering the drawbacks of existing harmonization datasets, we also contribute a ccHarmony dataset which simulates the natural illumination variation. Extensive experiments on iHarmony4 and our contributed dataset demonstrate the superiority of our method. Our ccHarmony dataset is released at https://github.com/bcmi/Image-Harmonization-Dataset-ccHarmony.