Drive-WM

Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving

Yuqi Wang*, Jiawei He*, Lue Fan*, Hongxin Li*, Yuntao Chen†, Zhaoxiang Zhang† (*: Equal Contribution; †: Corresponding Author)

[arXiv] [Project page]

TO DO

• Conditional image generation model weights (coming soon🚀)
• Conditional video generation model weights
• Action-conditioned video forecast model weights
• Training codes for all models

Get Started

Our code is based on the open-source project diffusers.

Citation

@article{wang2023driving,
  title={Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving},
  author={Wang, Yuqi and He, Jiawei and Fan, Lue and Li, Hongxin and Chen, Yuntao and Zhang, Zhaoxiang},
  journal={arXiv preprint arXiv:2311.17918},
  year={2023}
}

Acknowledgement

Many thanks to the following open-source projects:

• diffusers