Automatic semantic style transfer using deep convolutional neural networks and soft masks

• Published in: The Visual computer Vol. 36; no. 7; pp. 1307 - 1324
• Main Authors: Zhao, Hui-Huang, Rosin, Paul L., Lai, Yu-Kun, Wang, Yao-Nan
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.07.2020; Springer Nature B.V
• Subjects: Artificial Intelligence; Artificial neural networks; Computer Graphics; Computer Science; Fields (mathematics); Image Processing and Computer Vision; Masks; Methods; Neural networks; Object recognition; Original Article; Semantics; Style transfer; Deep neural networks; Soft mask; Semantic segmentation
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-019-01726-2

This paper presents an automatic image synthesis method to transfer the style of an example image to a content image. When standard neural style transfer approaches are used, the textures and colours in different semantic regions of the style image are often applied inappropriately to the content image, ignoring its semantic layout and ruining the transfer result. In order to reduce or avoid such effects, we propose a novel method based on automatically segmenting the objects and extracting their soft semantic masks from the style and content images, in order to preserve the structure of the content image while having the style transferred. Each soft mask of the style image represents a specific part of the style image, corresponding to the soft mask of the content image with the same semantics. Both the soft masks and source images are provided as multichannel input to an augmented deep CNN framework for style transfer which incorporates a generative Markov random field model. The results on various images show that our method outperforms the most recent techniques.