Controlling Geometric Abstraction and Texture for Artistic Images

1Hasso Plattner Institute, University of Potsdam, Germany 2Digitalmasterpieces GmbH, Germany
*equal contribution
Controlling Geometric Abstraction and Texture for Artistic Images.

Texture editing (left) and geometric editing (right) of artistic images.

Abstract

We present a novel method for the interactive control of geometric abstraction and texture in artistic images. Previous example-based stylization methods often entangle shape, texture, and color, while generative methods for image synthesis generally either make assumptions about the input image, such as only allowing faces, or do not offer precise editing controls By contrast, our holistic approach spatially decomposes the input into shapes and a parametric representation of high-frequency details comprising the image's texture, thus enabling independent control of color and texture. Each parameter in this representation controls painterly attributes of a pipeline of differentiable stylization filters. The proposed decoupling of shape and texture enables various options for stylistic editing, including interactive global and local adjustments of shape, stroke, and painterly attributes such as surface relief and contours. Additionally, we demonstrate optimization-based texture style-transfer in the parametric space using reference images and text prompts, as well as the training of single- and arbitrary style parameter prediction networks for real-time texture decomposition.

Method and Interactive Demonstration

BibTeX


@article{buessemeyer2023texcontrol,
  author    = { Büßemeyer, Martin and Reimann, Max and Buchheim, Benito and Semmo, Amir and Döllner, Jürgen and Trapp, Matthias},
  title     = {Controlling Geometric Abstraction and Texture for Artistic Images},
  journal   = {arXiv preprint arXiv:2308.00148},
  year      = {2023},
}     

Acknowledgements

Our work "Controlling Geometric Abstraction and Texture for Artistic Images" work was partially funded by the German Federal Ministry of Education and Research (BMBF) through grants 01IS15041 – “mdViPro” and 01IS19006 – “KI-Labor ITSE” .


Hasso-Plattner-Institut
Digital Masterpieces
BMBF: Bundesministerium für Bildung und Forschung
Universität Potsdam