Stroke Patches: Customizable Artistic Image Styling Using Regression
By: Ian Jaffray, John Bronskill
Potential Business Impact:
Makes pictures look like paintings with brush strokes.
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.
Similar Papers
Birth of a Painting: Differentiable Brushstroke Reconstruction
CV and Pattern Recognition
Makes computers paint pictures like humans do.
ScriptViT: Vision Transformer-Based Personalized Handwriting Generation
CV and Pattern Recognition
Makes computer handwriting look like real people's writing.
Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch Generation
CV and Pattern Recognition
Makes drawings look like a specific artist's style.