Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes

Dmytro Kotovenko, Matthias Wright, Arthur Heimbrecht, Bjorn Ommer

CVPR 2021 pp. 12196-12205

doi:10.1109/CVPR46437.2021.01202 /cvpr/2021/kotovenko2021cvpr-rethinking/

Abstract

There have been many successful implementations of neural style transfer in recent years. In most of these works, the stylization process is confined to the pixel domain. However, we argue that this representation is unnatural because paintings usually consist of brushstrokes rather than pixels. We propose a method to stylize images by optimizing parameterized brushstrokes instead of pixels and further introduce a simple differentiable rendering mechanism. Our approach significantly improves visual quality and enables additional control over the stylization process such as controlling the flow of brushstrokes through user input. We provide qualitative and quantitative evaluations that show the efficacy of the proposed parameterized representation.

PDF CVPR Semantic Scholar

Cite

Text

Kotovenko et al. "Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.01202

Markdown

[Kotovenko et al. "Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/kotovenko2021cvpr-rethinking/) doi:10.1109/CVPR46437.2021.01202

BibTeX

@inproceedings{kotovenko2021cvpr-rethinking,
  title     = {{Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes}},
  author    = {Kotovenko, Dmytro and Wright, Matthias and Heimbrecht, Arthur and Ommer, Bjorn},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {12196-12205},
  doi       = {10.1109/CVPR46437.2021.01202},
  url       = {https://mlanthology.org/cvpr/2021/kotovenko2021cvpr-rethinking/}
}