StarVector: Generating Scalable Vector Graphics Code from Images
Research paper by Juan A. Rodriguez and collaborators. Published 2023-12-17. Topics: Code Generation Large Language Models, CodeLLMs, CLIP image encoder, visual tokens, SVG token embeddings.
Resource information
- Authors
- Juan A. Rodriguez, Abhay Puri, Shubham Agarwal, Issam H. Laradji, Pau Rodriguez, Sai Rajeswar, David Vazquez, Christopher Pal, Marco Pedersoli
- Research area
- Computer vision
- Application domain
- General AI research
- AI methods
- Large language models
- Research topics
- cs.CV, cs.AI, cs.CL
- arXiv record date
- 2025-05-31
- Publication date
- 2023-12-17
- Publication
- arXiv
- Upstream last modified
- Jun 3, 2025
- License
- CC BY 4.0
- Last record update
- Nov 3, 2026
Abstract
Scalable Vector Graphics (SVGs) are vital for modern image rendering due to their scalability and versatility. Previous SVG generation methods have focused on curve-based vectorization, lacking semantic understanding, often producing artifacts, and struggling with SVG primitives beyond path curves. To address these issues, we introduce StarVector, a multimodal large language model for SVG generation. It performs image vectorization by understanding image semantics and using SVG primitives for compact, precise outputs. Unlike traditional methods, StarVector works directly in the SVG code space, leveraging visual understanding to apply accurate SVG primitives. To train StarVector, we create SVG-Stack, a diverse dataset of 2M samples that enables generalization across vectorization tasks and precise use of primitives like ellipses, polygons, and text. We address challenges in SVG evaluation, showing that pixel-based metrics like MSE fail to capture the unique qualities of vector graphics. We introduce SVG-Bench, a benchmark across 10 datasets, and 3 tasks: Image-to-SVG, Text-to-SVG generation, and diagram generation. Using this setup, StarVector achieves state-of-the-art performance, producing more compact and semantically rich SVGs.