构建可扩展矢量图形的连续稠密潜在空间，支持高效生成与操作。
A Scalable Vector Graphics Latent Space
- 基于Transformer的自编码器，统一建模SVG命令与坐标数据
- 学习固定尺寸潜在表示，还原时保持风格一致且高保真
- 潜在空间结构化，支持向量运算与跨任务泛化
可缩放矢量图形（SVG）是实现分辨率无关视觉内容的基础媒介，但深度学习领域缺乏连续、稠密且可逆的矢量表示潜在空间——这正是变分自编码器及其衍生方法为位图图像提供的基础构建模块。本文提出SLS（SVG潜在空间），一种基于Transformer的自编码器，能够学习单个SVG路径的紧凑稠密表示，这些路径是构成任意SVG图像的基本视觉单元。通过在统一的基于BPE的标记词汇表中建模SVG命令、坐标数据和视觉属性，SLS学习到固定大小的潜在表示，联合捕捉结构与外观，并能以高保真度解码回有效的、风格一致的SVG路径。所得到的嵌入空间具有鲁棒性、可逆性和结构性：嵌入位于单位超球面上，支持高效的相似性搜索、组合及通过简单的向量空间操作进行下游条件生成。最后，我们证明了SLS在多样化任务上具备泛化能力，相比基于标记的方法，其浮点运算量（FLOPs）降低超过150倍，为矢量图形研究建立了通用潜在基础。
原文摘要 · Abstract (English)
Scalable Vector Graphics are a fundamental medium for resolution-independent visual content, yet the deep learning community lacks a continuous, dense, and invertible latent space for vector representations, the kind of foundational building block that Variational Autoencoders and their descendants have long provided for raster images. We introduce SLS (SVG Latent Space), a Transformer-based autoencoder that learns compact dense representations of individual SVG paths, the atomic visual elements from which any SVG image can be composed. By modeling SVG commands, coordinate data, and visual properties within a unified BPE-based token vocabulary, SLS learns fixed-size latent representations that jointly capture structure and appearance, and can be decoded back into valid, style-consistent SVG paths with high fidelity. The resulting embedding space is robust, invertible, and structured: embeddings lie on a unit hypersphere, enabling efficient similarity search, composition, and downstream conditioning through simple vector-space operations. Finally, we demonstrate that SLS generalizes across diverse tasks reducing their FLOPs by over 150 times compared to token-based approaches, and establishing a general-purpose latent foundation for vector graphics research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。