RoboSVG:一种用于多模态引导的交互式SVG生成的统一框架
RoboSVG: A Unified Framework for Interactive SVG Generation with Multi-modal Guidance
AI总结:
RoboSVG提出统一多模态框架,利用文本、视觉和数值引导生成交互式SVG,并构建百万级RoboDraw数据集,在多项任务上达到最先进性能。
摘要:
可缩放矢量图形(SVG)是数字设计和机器人控制的基础,不仅编码视觉结构,还编码交互式绘图中的运动路径。在这项工作中,我们引入了RoboSVG,一个统一的多模态框架,用于在文本、视觉和数值信号的引导下生成交互式SVG。给定一个输入查询,RoboSVG模型首先产生多模态引导,然后通过专门的生成模块合成候选SVG,最后在数值引导下对其进行细化以产生高质量的输出。为了支持这一框架,我们构建了RoboDraw,一个包含一百万个示例的大规模数据集,每个示例将一个SVG生成条件(例如,文本、图像和部分SVG)与其对应的真实SVG代码配对。RoboDraw数据集使得对四个任务的系统研究成为可能,包括基础生成(文本到SVG、图像到SVG)和交互式生成(部分SVG到SVG、部分图像到SVG)。大量实验表明,RoboSVG在各种任务中实现了优越的查询合规性和视觉保真度,在多功能SVG生成中确立了新的最先进水平。该数据集和项目的源代码将很快公开。
英文摘要:
Scalable Vector Graphics (SVGs) are fundamental to digital design and robot control, encoding not only visual structure but also motion paths in interactive drawings. In this work, we introduce RoboSVG, a unified multimodal framework for generating interactive SVGs guided by textual, visual, and numerical signals. Given an input query, the RoboSVG model first produces multimodal guidance, then synthesizes candidate SVGs through dedicated generation modules, and finally refines them under numerical guidance to yield high-quality outputs. To support this framework, we construct RoboDraw, a large-scale dataset of one million examples, each pairing an SVG generation condition (e.g., text, image, and partial SVG) with its corresponding ground-truth SVG code. RoboDraw dataset enables systematic study of four tasks, including basic generation (Text-to-SVG, Image-to-SVG) and interactive generation (PartialSVG-to-SVG, PartialImage-to-SVG). Extensive experiments demonstrate that RoboSVG achieves superior query compliance and visual fidelity across tasks, establishing a new state of the art in versatile SVG generation. The dataset and source code of this project will be publicly available soon.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。