Diverse Image Harmonization

TL;DR

This paper introduces a novel image harmonization approach that generates multiple plausible results by modeling diverse foreground reflectances, improving flexibility and realism in composite images.

Contribution

It proposes a reflectance-guided harmonization network combined with a diverse reflectance generation network for multiple plausible harmonization outcomes.

Findings

Outperforms existing methods on benchmark datasets

Achieves more realistic and diverse harmonization results

Demonstrates the effectiveness of modeling multiple reflectances

Abstract

Image harmonization aims to adjust the foreground illumination in a composite image to make it harmonious. The existing harmonization methods can only produce one deterministic result for a composite image, ignoring that a composite image could have multiple plausible harmonization results due to multiple plausible reflectances. In this work, we first propose a reflectance-guided harmonization network, which can achieve better performance with the guidance of ground-truth foreground reflectance. Then, we also design a diverse reflectance generation network to predict multiple plausible foreground reflectances, leading to multiple plausible harmonization results. The extensive experiments on the benchmark datasets demonstrate the effectiveness of our method.