MM-SVGEdit：面向UI设计的多模态驱动SVG编辑
MM-SVGEdit: A Multimodal-Driven SVG Editing for UI Design
- Beihang University（北京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对传统SVG编辑门槛高和LLM方法可控性差的问题，提出多模态驱动的MM-SVGEdit，采用视觉定位加修改的两阶段策略，支持指令和直接操作，在自建数据集上显著提升编辑准确率、效率和用户控制感，并降低资源消耗。
AI中文摘要：
在UI设计领域，可缩放矢量图形（SVG）被广泛用作设计媒介。然而，传统的SVG编辑技术入门门槛高，且需要繁琐的手动迭代，而基于大语言模型（LLM）的编辑解决方案则存在准确性低和用户可控性差的问题。为解决这些问题，我们提出了MM-SVGEdit，一种多模态驱动的SVG编辑方法，它整合了传统SVG编辑与基于LLM的方法。我们引入了一个两阶段策略，即先进行视觉定位，再进行修改。两个阶段都支持两种交互模态：自然语言指令和直接操作（鼠标和键盘）。我们在一个自构建的、从UI生成的14,476个问答对数据集上训练并评估了MM-SVGEdit，该数据集涵盖了针对单个和多个UI目标的11种编辑操作类型。结果表明，MM-SVGEdit提高了SVG编辑的准确性、效率和用户感知的控制力，同时减少了令牌消耗和响应时间。
英文摘要：
In the field of UI design, Scalable Vector Graphics (SVG) is widely used as a design medium. However, traditional SVG editing techniques have high entry barriers and require cumbersome manual iteration, while LLM-based editing solutions suffer from low accuracy and poor user controllability. To address these issues, we propose MM-SVGEdit, a multimodal-driven SVG editing approach that integrates traditional SVG editing and LLM-based methods. We introduce a two-stage strategy in which visual grounding is followed by modification. Both stages support two interaction modalities: natural language instructions and direct manipulation (mouse and keyboard). We trained and evaluated MM-SVGEdit on a self-constructed dataset of 14,476 question-answer pairs generated from UIs, covering 11 types of editing operations on both single and multiple UI targets. The results show that MM-SVGEdit improves SVG editing accuracy, efficiency, and user-perceived control while reducing token consumption and response time.
