让AI生成更准确、可编辑的SVG图形，像人类思考一样逐步构建。
SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation
- 通过分步生成并模拟人类绘图过程来提升指令遵循能力。
- 相比顶尖方法，生成的SVG更稳定、错误更少，且支持全部矢量原语。
- 适合需要精确编辑的设计师和自动化图形生成场景。
矢量图形（SVG）是一种基于代码的二维视觉表示形式。借助大语言模型（LLM）的进展，我们研究文本到SVG的生成任务，解决泛化能力弱和指令遵循差两大难题。提出SVGThinker——一种推理驱动的框架，使SVG代码生成过程与可视化步骤对齐，并支持全部SVG原语。该流程按序渲染每个原语，利用多模态模型对图像和代码进行标注，构建反映逐项添加过程的增量更新。基于此数据，采用监督微调训练的LLM显式输出中间推理链，增强鲁棒性，减少错误与幻觉。实验表明，相比现有最先进方法，SVGThinker生成的SVG更稳定、可编辑、质量更高，同时保留矢量图形的结构优势。不同于基于图像的方法，其输出支持精准、分层编辑，为设计、内容创作和自动图形生成开辟新方向。
原文摘要 · Abstract (English)
Scalable Vector Graphics (SVG) is a code-based representation for 2D visuals. Leveraging recent advances in large language models (LLMs), we study text-to-SVG generation and address two persistent gaps: weak generalization and poor adherence to input instructions. We present SVGThinker, a reasoning-driven framework that aligns the production of SVG code with the visualization process and supports the full set of SVG primitives. Our pipeline first renders each primitive in sequence and uses a multimodal model to annotate the image and code; we then build stepwise updates that mirror the incremental addition of primitives. On this data, we train an LLM with supervised fine-tuning that exposes its chain-of-thought as intermediate reasoning, improving robustness and reducing errors and hallucinations. Experiments against state-of-the-art baselines show that SVGThinker produces more stable, editable, and higher-quality SVGs while preserving the structural advantages of vector graphics. Unlike image-based methods, our outputs enable precise and hierarchical editing, opening new directions for design, content creation, and automated graphics generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。