SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909643949735936 |
|---|---|
| author | Tang, Wenxin Xiao, Jingyu Jiang, Wenxuan Xiao, Xi Wang, Yuhang Tang, Xuxin Li, Qing Ma, Yuehe Liu, Junliang Tang, Shisong Lyu, Michael R. |
| author_facet | Tang, Wenxin Xiao, Jingyu Jiang, Wenxuan Xiao, Xi Wang, Yuhang Tang, Xuxin Li, Qing Ma, Yuehe Liu, Junliang Tang, Shisong Lyu, Michael R. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07964 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design Tang, Wenxin Xiao, Jingyu Jiang, Wenxuan Xiao, Xi Wang, Yuhang Tang, Xuxin Li, Qing Ma, Yuehe Liu, Junliang Tang, Shisong Lyu, Michael R. Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.07964 |