Style Transfer with Content Preservation from Multiple Images

Artistic style transfer is an image synthesis problem where the style of input image is reproduced with the style of given examples. Recent works show that artistic style transfer can be achieved by using hidden activations of a pretrained model. However, most existing methods only allow one example image representing style. In this work, we propose a framework based on neural patches matching that combines the content structure and style textures in a fusion layer of the network. Our method is capable to extract the style from a group of images, such as the paintings of specific painter. In particular, our method can preserve the original content information. Furthermore, by using multiple style images our approach can obtain desirable synthesis results in foreground objects.