English

SAMVG: A Multi-stage Image Vectorization Model with the Segment-Anything Model

Computer Vision and Pattern Recognition 2023-12-27 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2311.05276,
  title  = {SAMVG: A Multi-stage Image Vectorization Model with the Segment-Anything Model},
  author = {Haokun Zhu and Juang Ian Chong and Teng Hu and Ran Yi and Yu-Kun Lai and Paul L. Rosin},
  journal= {arXiv preprint arXiv:2311.05276},
  year   = {2023}
}

Comments

Accepted by ICASSP 2024

R2 v1 2026-06-28T13:16:01.155Z