SVGen: Interpretable Vector Graphics Generation with Large Language Models

作者：Feiyu Wang, Zhiyuan Zhao, Yuandong Liu, Da Zhang, Junyu Gao, Hao Sun, Xuelong Li · 年份：2025 · DOI：10.1145/3746027.3755011 · 被引用次数：2 · 研究领域：Multimodal Machine Learning Applications、Handwritten Text Recognition Techniques、Natural Language Processing Techniques

Scalable Vector Graphics (SVG) has become an indispensable technology in front-end development and UI/UX design, due to its inherent advantages in scalability, editability, and rendering efficiency. In the creation of vector graphics, while expressing creative concepts is straightforward, translating them into precise digital artworks is often challenging and time-consuming. To overcome this technical bottleneck and achieve intelligent conversion from concept to final product, we have constructed SVG-1M, a large-scale dataset of high-quality SVG samples with paired textual descriptions. Through innovative data augmentation and annotation processes, we built precisely aligned ''Text instruction-SVG code'' training pairs, with a subset enhanced by Chain-of-Thought (CoT) annotations. This provides rich semantic supervision signals for model learning. Based on this dataset, we propose SVGen, an end-to-end generative model capable of directly converting natural language descriptions into SVG code. This design addresses the challenges of generating semantically accurate vector graphics while preserving complete structural information. We explored various training strategies and introduced a progressive curriculum learning approach, optimized with reinforcement learning algorithms. Notably, this study innovatively applies the CoT paradigm to vector graphics generation, effectively enhancing both the accuracy and interpretability of SVG synthesis. Experimental validation demonstrates...