Split and Match: Example-based Adaptive Patch Sampling for Unsupervised Style Transfer

Oriel Frigo (University Paris Descartes / Technicolor), Neus Sabater (Technicolor) Julie Delon (University Paris Descartes), Pierre Hellier (Technicolor)


This paper presents a novel unsupervised method to transfer the style of an example image to a source image. The complex notion of image style is here considered as a local texture transfer, eventually coupled with a global color transfer. For the local texture transfer, we propose a new patch-based method based on an adaptive partition that captures the style of the example image and preserves the structure of the source image. More precisely, this example-based partition predicts how well a source patch matches an example patch. Results on various images show that out method outperforms the most recent techniques.




Some results:

Example 1: Van Gogh's Starry Night Example 2: Seurat's Woman

Input 1: Cat image Input 1, stylized by Example 1 Input 1, stylized by Example 2

Input 2: Venice image Input 2, stylized by Example 1 Input 2, stylized by Example 2