StyleSketch

StyleSketch is a method for extracting high-resolution stylized sketches from face images, utilizing the rich semantics of deep features from a pretrained StyleGAN. It is designed for individuals looking to create artistic and concise representations of faces.
StyleSketch works by training a sketch generator that accepts deep features as input, utilizing part-based losses with two-stage learning for fast convergence during training. This results in high-quality sketch extraction, outperforming existing state-of-the-art sketch extraction methods.
StyleSketch is particularly valuable for artists, designers, and researchers who need to extract and edit facial sketches, as it provides a means to express artistic intention while maintaining the identity of the person. It can also be extended to other domains, offering a versatile tool for various applications.