.png){kind=icon}
返回
MapGenerator: a framework for learning a diffusion model for text promptable map generation
.png){kind=icon}
PRE
AI
DOI：10.1080/15230406.2025.2587273.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Automated map generation, especially generating maps from natural language descriptions, not only democratizes access to geographic data but also strengthens decision-making, improves communication and allows for customization. However, map generation faces some challenges, such as lowering the professional threshold, improving generation quality, and ensuring geographic consistency. In recent years, large generative models (e.g. text-to-image models) have excelled in the field of image generation. However, since these models are primarily trained on natural image data, they exhibit significant gaps when generating map data with unique layouts and symbols designed. To address this, we propose a text-to-map generation framework based on diffusion model, called MapGenerator. By using a strategy that combines self-instruct and expert refinement, we construct the training dataset MGTrain and the evaluation dataset MGEval, containing 1000 and 100 pairs of maps and their corresponding detailed descriptions, respectively. Based on the training data, we employ a Parameter-Efficient Fine-Tuning (PEFT) strategy to fine-tune a pre-trained general text-to-image model, enhancing its performance in map generation tasks. Experimental results show that MapGenerator achieves the best FID and CLIP Score among all models, and expert evaluations confirm its superior ability to accurately capture geographic objects and spatial relationships described in the text. The study confirms the feasibility and effectiveness of the diffusion model-based text-to-map generation approach, offering new solutions and technical support for text-driven geographic information generation.
Keyword:
Automated map generation
Text-to-image models
diffusion models
geographic information
parameter-efficient fine-tuning
期刊
IF:
2.4
论文数:
103
被引数:
1.5K
机构
引用论文
MapGPT: an autonomous framework for mapping by integrating large language model and cartographic toolsMapGPT: 集成大型语言模型和制图工具的自主制图框架
.png){kind=icon}
PREAI
分享收藏MapReader: a framework for learning a visual language model for map analysisMapReader: 用于学习地图分析的视觉语言模型的框架
PREAI
分享收藏分享收藏SMAPGAN: Generative Adversarial Network-Based Semisupervised Styled Map Tile Generation MethodSMAPGAN: 基于生成对抗网络的半监督样式地图瓦片生成方法
OAAI
OAAI分享收藏
查看更多内容