AerialGo: Walking-through City View Generation from Aerial Perspectives
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913591962107904 |
|---|---|
| author | Zhao, Fuqiang Guo, Yijing Yang, Siyuan Chen, Xi Wang, Luo Xu, Lan Zhang, Yingliang Shi, Yujiao Yu, Jingyi |
| author_facet | Zhao, Fuqiang Guo, Yijing Yang, Siyuan Chen, Xi Wang, Luo Xu, Lan Zhang, Yingliang Shi, Yujiao Yu, Jingyi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00157 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AerialGo: Walking-through City View Generation from Aerial Perspectives Zhao, Fuqiang Guo, Yijing Yang, Siyuan Chen, Xi Wang, Luo Xu, Lan Zhang, Yingliang Shi, Yujiao Yu, Jingyi Computer Vision and Pattern Recognition Machine Learning 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. |
| title | AerialGo: Walking-through City View Generation from Aerial Perspectives |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2412.00157 |