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.

翻译：给定一幅合成图像，图像和谐化旨在调整前景光照使其与背景一致。先前的方法通过探索前景特征变换实现了具有竞争力的性能。本文研究表明，利用全局信息引导前景特征变换可取得显著提升。此外，我们提出将真实图像中的前景-背景关系迁移至合成图像，从而为变换后的编码器特征提供中间监督。考虑到现有和谐化数据集的缺陷，我们进一步贡献了模拟自然光照变化的ccHarmony数据集。在iHarmony4及我们贡献的数据集上的大量实验证明了本方法的优越性。我们的ccHarmony数据集已发布于https://github.com/bcmi/Image-Harmonization-Dataset-ccHarmony。