Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2508.18531 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914005633728512 |
|---|---|
| author | Jin, Zhangyu Feng, Andrew |
| author_facet | Jin, Zhangyu Feng, Andrew |
| contents | We present SatSkylines, a 3D building generation approach that takes satellite imagery and coarse geometric priors. Without proper geometric guidance, existing image-based 3D generation methods struggle to recover accurate building structures from the top-down views of satellite images alone. On the other hand, 3D detailization methods tend to rely heavily on highly detailed voxel inputs and fail to produce satisfying results from simple priors such as cuboids. To address these issues, our key idea is to model the transformation from interpolated noisy coarse priors to detailed geometries, enabling flexible geometric control without additional computational cost. We have further developed Skylines-50K, a large-scale dataset of over 50,000 unique and stylized 3D building assets in order to support the generations of detailed building models. Extensive evaluations indicate the effectiveness of our model and strong generalization ability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18531 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priors Jin, Zhangyu Feng, Andrew Computer Vision and Pattern Recognition Artificial Intelligence We present SatSkylines, a 3D building generation approach that takes satellite imagery and coarse geometric priors. Without proper geometric guidance, existing image-based 3D generation methods struggle to recover accurate building structures from the top-down views of satellite images alone. On the other hand, 3D detailization methods tend to rely heavily on highly detailed voxel inputs and fail to produce satisfying results from simple priors such as cuboids. To address these issues, our key idea is to model the transformation from interpolated noisy coarse priors to detailed geometries, enabling flexible geometric control without additional computational cost. We have further developed Skylines-50K, a large-scale dataset of over 50,000 unique and stylized 3D building assets in order to support the generations of detailed building models. Extensive evaluations indicate the effectiveness of our model and strong generalization ability. |
| title | SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priors |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.18531 |