---
license: mit
pipeline_tag: image-to-3d
---

# Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image

Sat3DGen is a framework for generating street-level 3D scenes from a single satellite image. It uses a geometry-first methodology to bridge the extreme viewpoint gap between satellite and street views, achieving high geometric fidelity and photorealism.

[**Paper**](https://arxiv.org/abs/2605.14984) | [**Project Page**](https://qianmingduowan.github.io/Sat3DGen_project_page/) | [**GitHub**](https://github.com/qianmingduowan/Sat3DGen) | [**Demo**](https://huggingface.co/spaces/qian43/Sat3DGen)

## Sample Usage

To use this model, you will need the code from the [official repository](https://github.com/qianmingduowan/Sat3DGen).

```python
from source.generator import Sat3DGen

# Load the model
Sat3DGen._skip_backbone_weights = True
model = Sat3DGen.from_pretrained("qian43/Sat3DGen")
model = model.to("cuda:0").eval()

# Proceed with inference as described in the repository
```

## Citation

If you find this work useful for your research, please cite:

```bibtex
@inproceedings{
    qian2026satdgen,
    title={Sat3{DG}en: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image},
    author={Ming Qian and Zimin Xia and Changkun Liu and Shuailei Ma and Wen Wang and Zeran Ke and Bin Tan and Hang Zhang and Gui-Song Xia},
    booktitle={The Fourteenth International Conference on Learning Representations},
    year={2026},
    url={https://openreview.net/forum?id=E7JzkZCofa}
}

@ARTICLE{Qian_2026_Sat2Densitypp,
    author={Qian, Ming and Tan, Bin and Wang, Qiuyu and Zheng, Xianwei and Xiong, Hanjiang and Xia, Gui-Song and Shen, Yujun and Xue, Nan},
    journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
    title={Seeing Through Satellite Images at Street Views}, 
    year={2026},
    volume={48},
    number={5},
    pages={5692-5709},
    doi={10.1109/TPAMI.2026.3652860}}

@InProceedings{Qian_2023_Sat2Density,
    author    = {Qian, Ming and Xiong, Jincheng and Xia, Gui-Song and Xue, Nan},
    title     = {Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
    pages     = {3683-3692}
}
```