High-quality 3D urban reconstruction is essential for applications in urban planning, navigation, and AR/VR. However, capturing detailed ground-level data across cities is both labor-intensive and raises significant privacy concerns related to sensitive information, such as vehicle plates, faces, and other personal identifiers. To address these challenges, we propose AerialGo, a novel framework that generates realistic walking-through city views from aerial images, leveraging multi-view diffusion models to achieve scalable, photorealistic urban reconstructions without direct ground-level data collection. By conditioning ground-view synthesis on accessible aerial data, AerialGo bypasses the privacy risks inherent in ground-level imagery. To support the model training, we introduce AerialGo dataset, a large-scale dataset containing diverse aerial and ground-view images, paired with camera and depth information, designed to support generative urban reconstruction. Experiments show that AerialGo significantly enhances ground-level realism and structural coherence, providing a privacy-conscious, scalable solution for city-scale 3D modeling.
@article{arxiv.2412.00157,
title = {AerialGo: Walking-through City View Generation from Aerial Perspectives},
author = {Fuqiang Zhao and Yijing Guo and Siyuan Yang and Xi Chen and Luo Wang and Lan Xu and Yingliang Zhang and Yujiao Shi and Jingyi Yu},
journal= {arXiv preprint arXiv:2412.00157},
year = {2024}
}