Skip to content

Official implementation of paper "Controllable 3D Outdoor Scene Generation"

License

Notifications You must be signed in to change notification settings

yuhengliu02/control-3d-scene

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

Controllable 3D Outdoor Scene Generation

Visitors

Teaser

Three-dimensional scene generation is crucial in computer vision, with applications spanning autonomous driving, gaming and the metaverse. Current methods either lack user control or rely on imprecise, non-intuitive conditions. In this work, we propose a method that uses scene graphs—an accessible, user-friendly control format—to generate outdoor 3D scenes. We develop an interactive system that transforms a sparse scene graph into a dense BEV (Bird's Eye View) Embedding Layout, which guides a conditional diffusion model to generate 3D scenes that match the scene graph description. During inference, users can easily create or modify scene graphs to generate large-scale outdoor scenes. We create a large-scale dataset with paired scene graphs and 3D semantic scenes to train the BEV embedding and diffusion models. Experimental results show that our approach consistently produces high-quality 3D urban scenes closely aligned with the input scene graphs.

NEWS

  • [2024/11/15] Official repo is created, code will be released soon.

About

Official implementation of paper "Controllable 3D Outdoor Scene Generation"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published