用矢量图替代位图，提升界面设计转代码的还原度。
Reverse Browser: Vector-Image-to-Code Generator
- 以矢量图像为输入，改进图像转代码的精度
- 构建多个大规模训练数据集，支持模型学习
- 提出多尺度图像质量评估新指标，更贴近真实体验
自动化将用户界面设计转化为代码（图像转代码或图像转UI）是软件工程研究的热点。然而，现有主流方案在还原原始设计方面仍存在明显差距，如基准测试所示。本文另辟蹊径：采用矢量图像而非位图作为模型输入。为此，构建了多个大型训练数据集，并评估了现有图像质量评估（IQA）算法，提出一种新的多尺度评估指标。随后训练了一个大型开源权重模型，并讨论其局限性。
原文摘要 · Abstract (English)
Automating the conversion of user interface design into code (image-to-code or image-to-UI) is an active area of software engineering research. However, the state-of-the-art solutions do not achieve high fidelity to the original design, as evidenced by benchmarks. In this work, I approach the problem differently: I use vector images instead of bitmaps as model input. I create several large datasets for training machine learning models. I evaluate the available array of Image Quality Assessment (IQA) algorithms and introduce a new, multi-scale metric. I then train a large open-weights model and discuss its limitations.
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。