Stroke Patches: Customizable Artistic Image Styling Using Regression

2026-01-06

arXiv.org

AI Summary

Existing neural style transfer and diffusion models struggle to explicitly control the brushstroke composition and detail hierarchy inherent in artistic styles. This work proposes a regression-based image stylization method that leverages a procedurally generated, extensible set of brushstroke primitives to enable fine-grained manipulation of multidimensional attributes—including shape, size, orientation, density, color, and noise. By integrating a U-Net regression architecture, the approach preserves the structural integrity of the input image while allowing intuitive user-guided adjustments to stylistic details. Experimental results demonstrate that the method produces diverse, expressive, and highly customizable artistic images, effectively overcoming the black-box limitations of conventional style transfer techniques.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We present a novel, regression-based method for artistically styling images. Unlike recent neural style transfer or diffusion-based approaches, our method allows for explicit control over the stroke composition and level of detail in the rendered image through the use of an extensible set of stroke patches. The stroke patch sets are procedurally generated by small programs that control the shape, size, orientation, density, color, and noise level of the strokes in the individual patches. Once trained on a set of stroke patches, a U-Net based regression model can render any input image in a variety of distinct, evocative and customizable styles.

Problem

• artistic image styling
• stroke control
• customizable styles
• stroke patches
• image rendering

Innovation

• stroke patches
• regression-based styling
• procedural generation
• customizable artistic style
• U-Net