A Novel Architecture for Image Vectorization with Increasing Granularity

In vector graphics, images are described by mathematical formulas with full image details even after scaling. Most research on generating vector graphics from raster images adopt the approach of splicing graphic fragments, which cannot perfectly retain the original topological structure and details of images. In this paper, we propose TSVec, a novel model for generating high-quality vector graphics by raster images, which takes advantages of the vision transformer and image super-resolution to enhance the granularity of vectorization, especially suitable for dealing with low-resolution raster images. The experimental results show that the vector graphics generated by TSVec outperform the current unsupervised vector generation models.