{
  "added_at": "2026-10-17",
  "arxiv_id": "2406.16386",
  "arxiv_version_reviewed": "v3",
  "authors": [
    "Yuxuan Wan",
    "Chaozheng Wang",
    "Yi Dong",
    "Wenxuan Wang",
    "Shuqing Li",
    "Yintong Huo",
    "Michael Lyu"
  ],
  "bibtex_url": "https://awesomerea.org/papers/citations/paper-dcgen.bib",
  "citation": {
    "article_number": "FSE094",
    "container_title": "Proceedings of the ACM on Software Engineering",
    "issue": "FSE",
    "pages": "2099-2122",
    "publisher": "Association for Computing Machinery (ACM)",
    "sources": [
      "https://api.crossref.org/works/10.1145/3729364",
      "https://arxiv.org/pdf/2406.16386v3"
    ],
    "volume": "2"
  },
  "code_url": "https://github.com/WebPAI/DCGen",
  "date_basis": "ACM-deposited Crossref metadata gives 19 June 2025 for online and print publication; the article text labels the issue July 2025.",
  "date_basis_zh": "ACM 向 Crossref 提交的元数据将在线及印刷版出版日期列为 2025 年 6 月 19 日；论文正文将期次标为 2025 年 7 月。",
  "date_precision": "day",
  "description_en": "Recursively divides a webpage screenshot along visual separation lines, has a multimodal model generate HTML/CSS for each leaf segment, and assembles child code upward into the full page; evaluated with GPT-4o, Gemini and Claude models and a small developer study.",
  "description_zh": "沿视觉分隔线递归切分网页截图，由多模态模型为每个叶子片段生成 HTML/CSS，再将子片段代码逐级向上组装为完整页面；评估涵盖 GPT-4o、Gemini 与 Claude 系列模型以及一项小规模开发者研究。",
  "doi": "10.1145/3729364",
  "entry_url": "https://awesomerea.org/papers/paper-dcgen/",
  "entry_url_zh": "https://awesomerea.org/zh/papers/paper-dcgen/",
  "evidence_urls": [
    "https://doi.org/10.1145/3729364",
    "https://api.crossref.org/works/10.1145/3729364",
    "https://arxiv.org/abs/2406.16386",
    "https://github.com/WebPAI/DCGen/blob/22af69b238fb5aa967cf3f05985a25b52481105f/README.md",
    "https://huggingface.co/datasets/iforgott/DCGen/tree/70ee45d6183f4b93773f2235f396f3a59d775ea6"
  ],
  "first_arxiv_date": "2024-06-24",
  "id": "paper-dcgen",
  "json_url": "https://awesomerea.org/papers/paper-dcgen/record.json",
  "kind": "research",
  "markdown_url": "https://awesomerea.org/papers/paper-dcgen/index.md",
  "markdown_url_zh": "https://awesomerea.org/zh/papers/paper-dcgen/index.md",
  "metadata_notes": "This is a PACMSE journal article, volume 2, FSE issue, pages 2099–2122 (article FSE094). Its published title replaces the arXiv title 'Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach'. Author names follow the article text, which prints 'Michael Lyu', as does Crossref; the arXiv record lists 'Michael R. Lyu'. The ACM Digital Library copy could not be retrieved during review; the reviewed text is the 24-page ACM-format arXiv v3. The paper-linked repository has no license file at the pinned commit; the full dataset is hosted separately on Hugging Face without a dataset card.",
  "metadata_notes_zh": "这是 PACMSE 第 2 卷 FSE 专期的期刊论文，页码为 2099–2122（文章编号 FSE094）。正式标题取代了 arXiv 标题“Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach”。作者姓名以论文正文为准，正文与 Crossref 均写作“Michael Lyu”，arXiv 记录则为“Michael R. Lyu”。核查期间无法读取 ACM 数字图书馆版本；审阅文本为 24 页、ACM 排版的 arXiv v3。论文所链接的仓库在固定提交中没有许可证文件；完整数据集另存于 Hugging Face，未附数据集说明卡。",
  "pdf_url": "https://arxiv.org/pdf/2406.16386v3",
  "project_url": null,
  "publication_date": "2025-06-19",
  "publication_status": "journal-article",
  "record_type": "paper",
  "runtime_tested": false,
  "scope_limitations_en": "It reconstructs static visual layout as HTML/CSS, not interaction, JavaScript behavior or backend logic. Test pages are self-contained snapshots with images replaced by placeholders; the main evaluation samples 111 of 348 top-ranked sites, adds 80 harder GitHub Pages pages, and the usefulness study has four participants. Segmentation uses manually set thresholds, and assembly can still misarrange elements.",
  "scope_limitations_zh": "该方法以 HTML/CSS 重建静态视觉布局，不重建交互、JavaScript 行为或后端逻辑。测试页面是将图片替换为占位图的自包含快照；主要评测从 348 个热门网站中抽取 111 个，另加 80 个更复杂的 GitHub Pages 页面，可用性研究仅有四名参与者。分割依赖人工设定的阈值，组装阶段仍可能错排元素。",
  "targets": [
    "website"
  ],
  "title": "Divide-and-Conquer: Generating UI Code from Screenshots",
  "title_zh": "分而治之：从截图生成界面代码",
  "url": "https://doi.org/10.1145/3729364",
  "venue": "Proceedings of the ACM on Software Engineering (FSE 2025)",
  "verification": "source-reviewed",
  "verified_at": "2026-10-17",
  "why_fits_en": "A segment-wise method for rebuilding website layout from screenshots, complementing the benchmark-oriented website papers.",
  "why_fits_zh": "提供按区域分解、从截图重建网站布局的方法，与以基准评测为主的网站论文互为补充。",
  "year": 2025
}