Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes

TitleRethinking Style Transfer: From Pixels to Parameterized Brushstrokes
Publication TypeConference Proceedings
Year of Publication2021
AuthorsKotovenko, D, Wright, M, Heimbrecht, A, Ommer, B
Conference NameProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
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. How- ever, 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 en- ables 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.

URLhttps://compvis.github.io/brushstroke-parameterized-style-transfer/
Citation Key7041