用参考图生成可编辑幻灯片，提升布局与视觉一致性
SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design
- 基于图像分割与分层检索增强生成，拆解复杂设计任务
- 在布局保真度等指标上领先基线40.5分
- 适合需要高效生成专业幻灯片的设计师与研究者
手动制作幻灯片耗时且需专业知识。现有基于自然语言的LLM生成方法难以捕捉幻灯片的视觉与结构特征。为此，我们提出参考图到幻灯片生成任务，并构建首个基于新滑块复杂度度量的分级难度基准Slide2Code。提出SlideCoder框架，结合基于颜色梯度的分割算法与分层检索增强生成方法，实现布局感知的可编辑幻灯片生成。同时发布7B规模的开源模型SlideMaster，基于改进的逆向工程数据微调。实验表明，SlideCoder在布局保真度、执行准确率和视觉一致性上相比顶尖基线最高提升40.5分，表现优异。代码已公开于https://github.com/vinsontang1/SlideCoder。
原文摘要 · Abstract (English)
Manual slide creation is labor-intensive and requires expert prior knowledge. Existing natural language-based LLM generation methods struggle to capture the visual and structural nuances of slide designs. To address this, we formalize the Reference Image to Slide Generation task and propose Slide2Code, the first benchmark with difficulty-tiered samples based on a novel Slide Complexity Metric. We introduce SlideCoder, a layout-aware, retrieval-augmented framework for generating editable slides from reference images. SlideCoder integrates a Color Gradient-based Segmentation algorithm and a Hierarchical Retrieval-Augmented Generation method to decompose complex tasks and enhance code generation. We also release SlideMaster, a 7B open-source model fine-tuned with improved reverse-engineered data. Experiments show that SlideCoder outperforms state-of-the-art baselines by up to 40.5 points, demonstrating strong performance across layout fidelity, execution accuracy, and visual consistency. Our code is available at https://github.com/vinsontang1/SlideCoder.
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。