[NeurIPS 2024] DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
Python
87
15 commits
updated Dec 5, 2024
The official implementation of the paper:
DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
Yuqi Wang, Ke Cheng, Jiawei He, Qitai Wang, Hengchen Dai, Yuntao Chen, Fei Xia, and Zhaoxiang Zhang
📑 paper 🎬 video demos 📖 dataset 📢zhihu
Our code is based on the open-source project diffusers. The source code is organized in diffusers/examples/world_model
The following table shows the supported finetuned methods and datasets in this repo, and we will update it continuously.
| Method / Dataset | DrivingDojo | nuScenes | Waymo | OpenDV2K |
|---|---|---|---|---|
| Stable Video Diffusion | ✓ | ✓ | ✓ | |
| Action-Conditioned Video Generation | ✓ |
if you find our work useful in your research, please consider citing:
@article{wang2024drivingdojo,
title={DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model},
author={Wang, Yuqi and Cheng, Ke and He, Jiawei and Wang, Qitai and Dai, Hengchen and Chen, Yuntao and Xia, Fei and Zhang, Zhaoxiang},
journal={arXiv preprint arXiv:2410.10738},
year={2024}
}
Many thanks to the following open-source projects:
Python
98.7%
Jupyter Notebook
1.2%
[NeurIPS 2024] DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
Python
87
15 commits
updated Dec 5, 2024
The official implementation of the paper:
DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
Yuqi Wang, Ke Cheng, Jiawei He, Qitai Wang, Hengchen Dai, Yuntao Chen, Fei Xia, and Zhaoxiang Zhang
📑 paper 🎬 video demos 📖 dataset 📢zhihu
Our code is based on the open-source project diffusers. The source code is organized in diffusers/examples/world_model
The following table shows the supported finetuned methods and datasets in this repo, and we will update it continuously.
| Method / Dataset | DrivingDojo | nuScenes | Waymo | OpenDV2K |
|---|---|---|---|---|
| Stable Video Diffusion | ✓ | ✓ | ✓ | |
| Action-Conditioned Video Generation | ✓ |
if you find our work useful in your research, please consider citing:
@article{wang2024drivingdojo,
title={DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model},
author={Wang, Yuqi and Cheng, Ke and He, Jiawei and Wang, Qitai and Dai, Hengchen and Chen, Yuntao and Xia, Fei and Zhang, Zhaoxiang},
journal={arXiv preprint arXiv:2410.10738},
year={2024}
}
Many thanks to the following open-source projects:
Python
98.7%
Jupyter Notebook
1.2%