Abstract

Computer Vision-based Style Transfer techniques have been used for many years to represent artistic style. However, most contemporary methods have been restricted to the pixel domain; in other words, the style transfer approach has been modifying the image pixels to incorporate artistic style. However, real artistic work is made of brush strokes with different colors on a canvas. Pixel-based approaches are unnatural for representing these images. Hence, this paper discusses a style transfer method that represents the image in the brush stroke domain instead of the RGB domain, which has better visual improvement over pixel-based methods.

Methodology

Methodology

Results

Video Result

This video demonstrates the application of the parameterized brush strokes optimization using content and style transfer.

Image Results

Click on the image to zoom

This image shows the result of applying the style transfer technique to a bridge scene. Notice the intricate brush strokes and the overall artistic transformation.

GitHub LinkedIn Paper Presentation course-link

References

@article{kotovenko_cvpr_2021, title={Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes}, author={Dmytro Kotovenko and Matthias Wright and Arthur Heimbrecht and Bj{"o}rn Ommer}, journal={CVPR}, year={2021} }

Citation

@misc{meleti2024brushstroke, title={Brush Stroke Parameterized Style Transfer}, author={Uma Maheswara R Meleti}, year={2024}, url={https://github.com/maheshmeleti/brushstroke-parameterized-style-transfer-pytorch}, }