Parameterized Brushstroke Style Transfer
This work addresses the problem of unnatural artistic representations in style transfer for artists and users seeking more authentic digital art.
This paper proposes a style transfer method that operates in the brushstroke domain rather than the pixel domain. This approach aims to create a more natural representation of artistic work, leading to better visual improvement compared to pixel-based methods.
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.