Date: less than 1 minute read

CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion

Guangyao Zhai   Evin Pınar Örnek   Shun-Cheng Wu   Yan Di   Federico Tombari   Nassir Navab   Benjamin Busam  
Technical University of Munich   Google  




CommonScenes generates complete 3D indoor scenes from scene graphs using a diffusion-based approach. A VAE-based layout branch predicts object arrangements, while a latent diffusion shape branch synthesizes object geometries that populate the layout, producing coherent scenes that respect commonsense relationships encoded in the graph.

Paper

@inproceedings{zhai2023commonscenes,
  title={CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion},
  author={Zhai, Guangyao and {\"O}rnek, Evin P{\i}nar and Wu, Shun-Cheng and Di, Yan and Tombari, Federico and Navab, Nassir and Busam, Benjamin},
  booktitle={Advances in Neural Information Processing Systems},
  year={2023}
}

Code

Code is available at ymxlzgy/commonscenes.