English

Multiple Style Transfer via Variational AutoEncoder

Computer Vision and Pattern Recognition 2021-10-15 v1 Image and Video Processing

Abstract

Modern works on style transfer focus on transferring style from a single image. Recently, some approaches study multiple style transfer; these, however, are either too slow or fail to mix multiple styles. We propose ST-VAE, a Variational AutoEncoder for latent space-based style transfer. It performs multiple style transfer by projecting nonlinear styles to a linear latent space, enabling to merge styles via linear interpolation before transferring the new style to the content image. To evaluate ST-VAE, we experiment on COCO for single and multiple style transfer. We also present a case study revealing that ST-VAE outperforms other methods while being faster, flexible, and setting a new path for multiple style transfer.

Keywords

Cite

@article{arxiv.2110.07375,
  title  = {Multiple Style Transfer via Variational AutoEncoder},
  author = {Zhi-Song Liu and Vicky Kalogeiton and Marie-Paule Cani},
  journal= {arXiv preprint arXiv:2110.07375},
  year   = {2021}
}

Comments

5 papges, 4 figures

R2 v1 2026-06-24T06:53:15.806Z