Creative Style Transfer

Jun Li, Li Shi Min, Ze-dong Zhang, Gan Sun, Hongfu Liu, Li-wei H. Lehman, Jian YangOpenReview 2024 · Submission to ICLR 2024 · Withdrawn · OpenReview

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Generating novel artistic styles from a single style is a formidable challenge for for traditional style transfer techniques, which typically focus on emulating the provided style without introducing fresh and meaningful elements. In this paper, we propose a creativity process for producing new and meaningful artistic styles, called creative style transfer (CSFer). We first introduce a neural permutation network (PerNet) to rearrange the feature maps of a single style image, thereby adapting them to the feature maps of a content image, resulting in the desired stylization content. Essentially, this permutation process enriches the bases of the single style within a high-dimensional feature space, departing from the conventional linear combination of multiple styles. To gauge the quality of our stylized content, we leverage metrics encompassing content structure, style perception, and artistic aesthetics. These metrics enable us to assess our stylized content in comparison to the output produced by traditional style transfer methods. In the training phase, PerNet learns to generate high-quality stylized content by randomly sampling permutation matrices that yield high-quality stylization outcomes. Experimental results demonstrate that our CSFer can create novel and original stylization outcomes. Furthermore, CSFer exhibits robust generalization capabilities by simply inserting the PerNet into the style transfer methods.
BibTeX
@misc{li2024creative,
  author = {Jun Li and Li Shi Min and Ze-dong Zhang and Gan Sun and Hongfu Liu and Li-wei H. Lehman and Jian Yang},
  title = {{Creative Style Transfer}},
  year = {2024},
  url = {https://openreview.net/forum?id=vvROJOMYP8},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2024},
}
Figure