SAMVG: A multi-stage image vectorization model with the segment-anything model

Zhu, Haokun, Chong, Juang Ian, Hu, Teng, Yi, Ran, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884 2024. SAMVG: A multi-stage image vectorization model with the segment-anything model. Presented at: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, 14-19 April 2024. Proceedings of the 2024 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, pp. 4350-4354. 10.1109/ICASSP48485.2024.10447396

Preview

PDF - Accepted Post-Print Version Download (1MB) | Preview

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.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	IEEE
ISBN:	979-8-3503-4486-8
ISSN:	1520-6149
Date of First Compliant Deposit:	21 March 2024
Date of Acceptance:	13 December 2023
Last Modified:	13 May 2025 14:22
URI:	https://orca.cardiff.ac.uk/id/eprint/167441

Actions (repository staff only)

Edit Item