Deep Image Harmonization

TL;DR

This paper introduces a deep learning approach for image harmonization that effectively captures context and semantics, outperforming previous methods and utilizing a new large-scale training dataset.

Contribution

The authors propose an end-to-end deep convolutional neural network for image harmonization and a novel method for collecting high-quality training data.

Findings

Outperforms previous state-of-the-art methods

Effective in both synthesized and real composite images

Utilizes large-scale high-quality training data

Abstract

Compositing is one of the most common operations in photo editing. To generate realistic composites, the appearances of foreground and background need to be adjusted to make them compatible. Previous approaches to harmonize composites have focused on learning statistical relationships between hand-crafted appearance features of the foreground and background, which is unreliable especially when the contents in the two layers are vastly different. In this work, we propose an end-to-end deep convolutional neural network for image harmonization, which can capture both the context and semantic information of the composite images during harmonization. We also introduce an efficient way to collect large-scale and high-quality training data that can facilitate the training process. Experiments on the synthesized dataset and real composite images show that the proposed network outperforms previous state-of-the-art methods.