arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2504.06263cs.CV
收藏

OmniSVG: 一种统一的可扩展矢量图形生成模型

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Fudan University(复旦大学);StepFun Project(StepFun项目)

Yiying Yang, Wei Cheng, Sijin Chen, Xianfang Zeng, Fukun Yin, Jiaxu Zhang, Liao Wang, Gang Yu, Xingjun Ma, Yu-Gang Jiang

AI总结:

OmniSVG通过统一框架和预训练视觉-语言模型,实现高效多模态SVG生成,提升复杂结构的表达能力,并引入大规模数据集推动SVG合成发展。

摘要:

可扩展矢量图形(SVG)是一种重要的图像格式,在图形设计中广泛应用,因其分辨率无关性和可编辑性。生成高质量SVG的研究持续吸引了AIGC社区中设计师和研究人员的注意。然而,现有方法要么产生结构不明确的输出,计算成本高,要么局限于生成单色图标,结构过于简化。为了生成高质量且复杂的SVG,我们提出了OmniSVG,一种统一的框架,利用预训练的视觉-语言模型(VLMs)进行端到端的多模态SVG生成。通过将SVG命令和坐标参数化为离散的标记,OmniSVG将结构逻辑与低级几何分离,以提高训练效率,同时保持复杂SVG结构的表达能力。为进一步推动SVG合成的发展,我们引入了MMSVG-2M,一个包含两百万个丰富标注的SVG资产的多模态数据集,以及标准化的评估协议,用于条件SVG生成任务。广泛的实验表明,OmniSVG优于现有方法,并展示了其在专业SVG设计工作流程中的潜力。

英文摘要:

Scalable Vector Graphics (SVG) is an important image format widely adopted in graphic design because of their resolution independence and editability. The study of generating high-quality SVG has continuously drawn attention from both designers and researchers in the AIGC community. However, existing methods either produces unstructured outputs with huge computational cost or is limited to generating monochrome icons of over-simplified structures. To produce high-quality and complex SVG, we propose OmniSVG, a unified framework that leverages pre-trained Vision-Language Models (VLMs) for end-to-end multimodal SVG generation. By parameterizing SVG commands and coordinates into discrete tokens, OmniSVG decouples structural logic from low-level geometry for efficient training while maintaining the expressiveness of complex SVG structure. To further advance the development of SVG synthesis, we introduce MMSVG-2M, a multimodal dataset with two million richly annotated SVG assets, along with a standardized evaluation protocol for conditional SVG generation tasks. Extensive experiments show that OmniSVG outperforms existing methods and demonstrates its potential for integration into professional SVG design workflows.

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。

↑