Scalable Vector Graphics (SVG) is a popular vector image format that offers good support for interactivity and animation. Despite its appealing characteristics, creating custom SVG content can be challenging for users due to the steep learning curve required to understand SVG grammars or get familiar with professional editing software. Recent advancements in text-to-image generation have inspired researchers to explore vector graphics synthesis using either image-based methods (i.e., text -> raster image -> vector graphics) combining text-to-image generation models with image vectorization, or language-based methods (i.e., text -> vector graphics script) through pretrained large language models. However, these methods still suffer from limitations in terms of generation quality, diversity, and flexibility. In this paper, we introduce IconShop, a text-guided vector icon synthesis method using autoregressive transformers. The key to success of our approach is to sequentialize and tokenize SVG paths (and textual descriptions as guidance) into a uniquely decodable token sequence. With that, we are able to fully exploit the sequence learning power of autoregressive transformers, while enabling both unconditional and text-conditioned icon synthesis. Through standard training to predict the next token on a large-scale vector icon dataset accompanied by textural descriptions, the proposed IconShop consistently exhibits better icon synthesis capability than existing image-based and language-based methods both quantitatively and qualitatively. Meanwhile, we observe a dramatic improvement in generation diversity, which is validated by the objective Uniqueness and Novelty measures. More importantly, we demonstrate the flexibility of IconShop with multiple novel icon synthesis tasks, including icon editing, icon interpolation, icon semantic combination, and icon design auto-suggestion.

翻译：可缩放矢量图形（SVG）是一种流行的矢量图像格式，能够良好支持交互性与动画效果。尽管其具有吸引人的特性，但由于用户需要理解SVG语法或熟悉专业编辑软件所面临的陡峭学习曲线，创作自定义SVG内容仍颇具挑战。近年来，文本到图像生成技术的进展激励研究者探索矢量图形合成方法：一类是基于图像的方法（即文本→光栅图像→矢量图形），通过结合文本生成图像模型与图像矢量化技术实现；另一类是基于语言的方法（即文本→矢量图形脚本），借助预训练大语言模型完成。然而，这些方法在生成质量、多样性与灵活性上仍存在局限。本文提出IconShop——一种基于自回归Transformer的文本引导矢量图标合成方法。该方法成功的关键在于将SVG路径（以及作为引导的文本描述）序列化与符号化，转化为唯一可解码的符号序列。由此，我们能够充分挖掘自回归Transformer的序列学习能力，同时实现无条件与文本条件驱动的图标合成。通过在包含文本描述的大规模矢量图标数据集上执行标准的下一个符号预测训练，所提出的IconShop在定量与定性评估中均展现出优于现有基于图像与基于语言方法的图标合成能力。此外，我们观察到生成多样性的显著提升，这一结论得到了客观的独特性与新颖性指标验证。更重要的是，我们通过多种新颖的图标合成任务——包括图标编辑、图标插值、图标语义组合及图标设计自动建议——展示了IconShop的灵活性。