Wasserstein Style Transfer is a Gaussian optimal transport for image style transfer in an Encoder/Decoder framework. Optimal transport for Gaussian measures has closed forms Monge mappings from source to target distributions. Interpolates between a content and a style image can be seen as geodesics in the Wasserstein Geometry. This page demonstrates how to mix different target styles using Wasserstein barycenter of Gaussian measures.

For further details, please check out the paper: https://arxiv.org/abs/1905.12828

Related work:

Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., and Yang, M. H. (2017). Universal style transfer via feature transforms. In Advances in neural information processing systems (pp. 386-396).

Huang, X., and Belongie, S. (2017). Arbitrary style transfer in real-time with adaptive instance normalization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1501-1510).