Compositional Generative Model of Unbounded 3D Cities

Official demo for CityDreamer: Compositional Generative Model of Unbounded 3D Cities (CVPR 2024).

🔥 CityDreamer is a unbounded 3D city generator.
🤗 Try CityDreamer to generate photolistic 3D cities.
⚠️ Due to the limited computational resources at Hugging Face, this demo only generates A SINGLE IMAGE based on the New York City layout. If you wish to experience more comprehensive functionality, please visit the demo on GitHub.

Camera Radius (m)

128 512

Camera Altitude (m)

256 512

Camera Azimuth (°)

0 360

Map Center (px)

1440 6752

Generated City

Citation 📝

If our work is useful for your research, please consider citing:

@inproceedings{xie2024citydreamer,
  title     = {City{D}reamer: Compositional Generative Model of Unbounded 3{D} Cities},
  author    = {Xie, Haozhe and 
               Chen, Zhaoxi and 
               Hong, Fangzhou and 
               Liu, Ziwei},
  booktitle = {CVPR},
  year      = {2024}
}

License 📋

This project is licensed under S-Lab License 1.0. Redistribution and use for non-commercial purposes should follow this license.