面向城市规划的图像生成技术
Image Generation Techniques for Urban Planning
浏览论文内容
中文总结 AI 辅助
本研究开发了基于掩码的加权条件流匹配（MWCFM）模型，用于自动生成城市场景中的建筑演示图像，并通过应用相关指标评估其性能，为城市规划图像生成提供优化方案。
中文摘要 AI 辅助
在城市规划场景中，建筑师通常需制作演示图像，以可视化拟建建筑在城市环境中的呈现效果。本研究旨在开发一款生成式人工智能（GenAI）模型，用于自动生成城市场景中的建筑演示图像，重点关注模型优化。为实现这一目标，我们开发了基于掩码的加权条件流匹配（Mask-based Weighted Conditional Flow Matching，MWCFM），该方法通过引入上下文掩码扩展了流匹配（Flow Matching），以实现精确的特征聚焦，支持针对城市规划相关的关键空间元素进行定向训练。我们训练的模型从城市街景数据中学习，同时遵循特定风格准则，这些准则通过损失函数被整合到训练过程中。此外，我们使用与应用相关的指标对模型性能进行评估，这些指标源自演示图像的风格准则。
英文摘要
In the context of urban planning, architects are normally instructed with creating presentation images that visualize proposed buildings within their urban context. This work aims to develop a GenAI model for automatically generating architectural presentation images in urban scenes, with emphasis on model optimization. To achieve this, we developed Mask-based Weighted Conditional Flow Matching (MWCFM), which extends Flow Matching by introducing contextual masks for precise feature focusing. This enables targeted training on critical spatial elements relevant to urban planning. Our trained model learns from urban street-view data while adhering to specific style-guidelines, which are integrated into training through the loss function. Furthermore, the model's performance is evaluated using application related metrics, derived from presentation image style guidelines.
