SAMVG: A Multi-stage Image Vectorization Model with the Segment-Anything Model
This addresses the problem of acquiring high-quality vector graphics for designers and artists, though it appears incremental as it builds on existing segmentation models.
The paper tackles the challenge of automatically converting complex raster images like photos into high-quality vector graphics (SVG) by proposing SAMVG, a multi-stage model that uses the Segment-Anything Model for segmentation and a novel filtering method, resulting in high-quality SVGs with less computation time and complexity compared to previous state-of-the-art methods.
Vector graphics are widely used in graphical designs and have received more and more attention. However, unlike raster images which can be easily obtained, acquiring high-quality vector graphics, typically through automatically converting from raster images remains a significant challenge, especially for more complex images such as photos or artworks. In this paper, we propose SAMVG, a multi-stage model to vectorize raster images into SVG (Scalable Vector Graphics). Firstly, SAMVG uses general image segmentation provided by the Segment-Anything Model and uses a novel filtering method to identify the best dense segmentation map for the entire image. Secondly, SAMVG then identifies missing components and adds more detailed components to the SVG. Through a series of extensive experiments, we demonstrate that SAMVG can produce high quality SVGs in any domain while requiring less computation time and complexity compared to previous state-of-the-art methods.