BargainNet: Background-Guided Domain Translation for Image Harmonization

TL;DR

BargainNet introduces a background-guided domain translation approach for image harmonization, leveraging background information to improve foreground adjustment, and demonstrates superior performance on benchmark datasets.

Contribution

The paper proposes a novel domain translation framework guided by background information, with a new domain code extractor and triplet losses for improved image harmonization.

Findings

Effective in aligning foreground with background domain.

Outperforms existing methods on benchmark datasets.

Code availability facilitates reproducibility.

Abstract

Image composition is a fundamental operation in image editing field. However, unharmonious foreground and background downgrade the quality of composite image. Image harmonization, which adjusts the foreground to improve the consistency, is an essential yet challenging task. Previous deep learning based methods mainly focus on directly learning the mapping from composite image to real image, while ignoring the crucial guidance role that background plays. In this work, with the assumption that the foreground needs to be translated to the same domain as background, we formulate image harmonization task as background-guided domain translation. Therefore, we propose an image harmonization network with a novel domain code extractor and well-tailored triplet losses, which could capture the background domain information to guide the foreground harmonization. Extensive experiments on the existing image harmonization benchmark demonstrate the effectiveness of our proposed method. Code is available at https://github.com/bcmi/BargainNet.