具有全局引导特征变换和关系蒸馏的深度图像和谐化
Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation
AI总结:
本文提出一种利用全局信息引导前景特征变换并结合关系蒸馏的深度图像和谐化方法,同时构建了模拟自然光照变化的ccHarmony数据集,显著提升了合成图像前景与背景光照一致性的调整效果。
摘要:
给定一张合成图像,图像和谐化旨在调整前景光照以与背景保持一致。以往的方法探索了变换前景特征以实现有竞争力的性能。在这项工作中,我们表明,使用全局信息来引导前景特征变换可以实现显著提升。此外,我们提出将真实图像中的前景-背景关系迁移到合成图像中,这可以为变换后的编码器特征提供中间监督。另外,考虑到现有和谐化数据集的缺陷,我们还贡献了一个模拟自然光照变化的 ccHarmony 数据集。在 iHarmony4 和我们贡献的数据集上的大量实验证明了我们方法的优越性。我们的 ccHarmony 数据集已在 https://github.com/bcmi/Image-Harmonization-Dataset-ccHarmony 发布。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。