paper-with-me

Papers

SVGen: Interpretable Vector Graphics Generation with Large Language Models

2025-08-06 · Feiyu Wang, Zhiyuan Zhao, Yuandong Liu, Da Zhang, Junyu Gao, Hao Sun, Xuelong Li arxiv

Scalable Vector Graphics (SVG) is widely used in front-end development and UI/UX design due to its scalability, editability, and rendering efficiency. However, turning creative ideas into precise vector graphics remains a time-consuming challenge. To address this, we introduce SVG-1M, a large-scale dataset of high-quality SVGs paired with natural language descriptions. Through advanced data augmentation and annotation, we create well-aligned Text to SVG training pairs, including a subset with Chain of Thought annotations for enhanced semantic guidance. Based on this dataset, we propose SVGen, an end-to-end model that generates SVG code from natural language inputs. Our approach ensures semantic accuracy and structural completeness, supported by curriculum learning and reinforcement learning optimization. Experiments show that SVGen outperforms general large models and traditional rendering methods in both effectiveness and efficiency. Code, model, and dataset are available on GitHub.

📄 PDF Abstract BibTeX arXiv:2508.09168

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningData Augmentation

Similar Papers 제목 키워드 기반

SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation

2025-06-03 · Siqi Chen, Xinyu Dong, Haolei Xu, Xingyu Wu 외

Large Language Models (LLMs) and Multimodal LLMs have shown promising capabilities for SVG processing, yet existing benchmarks suffer from limited real-world coverage, lack of complexity stratification, and fragmented ev…

BenchmarkingStyle TransferVector Graphics

Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure

2025-12-16 · Jooyeol Yun, Jaegul Choo arxiv

Scalable Vector Graphics (SVG) are central to modern web design, and the demand to animate them continues to grow as web environments become increasingly dynamic. Yet automating the animation of vector graphics remains c…

Code GenerationMotion Planning

Beyond Pixels: Exploring Human-Readable SVG Generation for Simple Images with Vision Language Models

2023-11-27 · Tong Zhang, Haoyang Liu, Peiyan Zhang, Yuxuan Cheng 외

In the field of computer graphics, the use of vector graphics, particularly Scalable Vector Graphics (SVG), represents a notable development from traditional pixel-based imagery. SVGs, with their XML-based format, are di…

Vector Graphics

Leveraging Large Language Models For Scalable Vector Graphics Processing: A Review

2025-03-06 · Boris Malashenko, Ivan Jarsky, Valeria Efimova

In recent years, rapid advances in computer vision have significantly improved the processing and generation of raster images. However, vector graphics, which is essential in digital design, due to its scalability and ea…

Vector Graphics

VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation

2024-07-15 · Bocheng Zou, Mu Cai, Jianrui Zhang, Yong Jae Lee

In the realm of vision models, the primary mode of representation is using pixels to rasterize the visual world. Yet this is not always the best or unique way to represent visual content, especially for designers and art…

Vector Graphics