Deep Image Harmonization

Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu, Ming-Hsuan Yang
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
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
more » ... utional 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 stateof-the-art methods.
doi:10.1109/cvpr.2017.299 dblp:conf/cvpr/TsaiSLSL017 fatcat:gd2ww7pfdnferdowtqiez6jx3m