DualControlNet：基于卫星影像生成土地利用图的生成式城市规AI方法

View PDF HTML (experimental)

Abstract:Various land-use models characterize land-use patterns and facilitate scenario planning. However, existing models are largely predictive, forecasting transitions based on numeric data without synthesizing new land-use maps from simple text prompts. Meanwhile, generative AI in urban systems remains unimodal, weakly controllable, and evaluated mostly by generic image quality rather than domain-specific metrics. To address these gaps, we introduce DualControlNet, a generative land-use model that jointly synthesizes high-resolution land-use maps and satellite imagery, addressing multimodality, controllability, and verification challenges. Trained on over 40,000 paired tiles from Orlando and Chicago, DualControlNet is evaluated using land-use, spatial consistency, and image quality metrics. Relative to unimodal baselines, DualControlNet improves land-use diversity consistency by 62.8% and building coverage ratio consistency by 16.3%, more than doubles cross-modal spatial consistency, and triples visual quality. Scenario-based experiments demonstrate that DualControlNet supports sustainable development through multidimensional controls, increasing density and diversity, and responding to text prompts like "high-density development." Overall, this work advances land-use modeling via a multimodal, controllable, and verifiable generative framework, lowering technical barriers and enabling intuitive exploration of urban futures.

Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2611.05859 [cs.CV]
	(or arXiv:2611.05859v1 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2611.05859 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Qingqi Song [view email]
[v1] Wed, 4 Nov 2026 02:49:55 UTC (8,809 KB)