VFIG:利用视觉-语言模型矢量化SVG中的复杂图形
VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
AI总结:
本文提出VFIG,一种基于视觉-语言模型的矢量化方法,通过大规模数据集和分层训练策略,实现复杂图形到SVG的高保真转换,并在基准测试中取得优异成绩。
摘要:
可扩展矢量图形(SVG)是技术 illustration 和数字设计的关键格式,提供精确的分辨率独立性和灵活的语义编辑性。然而,原始矢量源文件经常丢失或不可用,只剩下“扁平”的位图版本(如PNG或JPEG),难以修改或缩放。手动重建这些图形是一个极其耗费人力的过程,需要专业知识来恢复原始几何意图。为此,我们提出了VFIG,一个用于复杂和高保真图形到SVG转换的视觉-语言模型家族。虽然这项任务本质上是数据驱动的,但现有数据集通常规模小且缺乏专业图表的复杂性。我们通过引入VFIG-DATA,一个包含66,000对高质量图形-SVG的大型数据集,从多样化的现实论文图形和程序生成图表中精心挑选。认识到SVG由重复的原始构件和层次局部结构组成,我们引入了从粗到细的训练课程,从监督微调(SFT)学习原子构件,过渡到强化学习(RL)优化以优化全局图表保真度、布局一致性和拓扑边角情况。最后,我们引入了VFIG-BENCH,一个全面的评估套件,包含新的度量标准,用于测量复杂图形的结构完整性。VFIG在开源模型中取得了最先进的性能,并与GPT-5.2表现相当,在VFIG-BENCH上取得了0.829的VLM-Judge分数。
英文摘要:
Scalable Vector Graphics (SVG) are essential for technical illustration and digital design, offering resolution independence and semantic editability. In practice, original vector files are frequently lost, leaving only rasterized versions (e.g., PNG, JPEG) that resist modification, while manual reconstruction is prohibitively expensive. Progress on automating raster-to-SVG conversion has been bottlenecked by two gaps: existing SVG datasets are dominated by icons and decorative graphics that lack the complexity of professional diagrams, and existing benchmarks rely on pixel- or embedding-level similarity that fails to capture structural correctness (e.g., broken connectivity, misplaced arrows). We close both gaps with paired contributions targeting diagram-centric figures (e.g., model architectures, flowcharts, schematics). For training, we introduce VFIG-Data, the largest figure-to-SVG dataset of its kind at 66K pairs, combining real paper figures converted via a describe-and-generate pipeline with programmatic diagrams that supply noise-free supervision over arrow styles, fonts, and geometry. For evaluation, we introduce VFIG-Bench, a structure-aware evaluation suite, paired with VFIG-Bench-OOD, an out-of-distribution set of figures manually curated from highly cited arXiv papers. Beyond pixel and embedding similarity, our protocol reports rubric-based VLM-Judge scores and Elo ratings from pairwise human preference evaluation. Built on these contributions, VFIG is a VLM family trained with a simple-to-complex SFT curriculum followed by RL with rendering-aware rewards. VFIG achieves state-of-the-art open-source performance, outperforming the best open-source VLM baseline by over 30%, and matches Claude Sonnet 4.6 on VFIG-BENCH: Gemini-Judge 78.2% vs. 76.7% and GPT-Judge 87.5% vs. 87.4%. It remains slightly behind the strongest proprietary models GPT-5.2 and Gemini-3.
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。