Deep Image Harmonization

Yi-Hsuan Tsai Xiaohui Shen Zhe Lin Kalyan Sunkavalli Xin Lu Ming-Hsuan Yang

University of California, Merced Adobe Research


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.


"Deep Image Harmonization", Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu, Ming-Hsuan Yang, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

[PDF] [Supplementary] [GitHub] [Evaluation Set]


author = {Y.-H. Tsai and X. Shen and Z. Lin and K. Sunkavalli and X. Lu and M.-H. Yang},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
title = {Deep Image Harmonization},
year = {2017}}