<div align="center"> <img src="assets/logo.png" width="80"> <h1>DiffusionDrive</h1> <h3>Truncated Diffusion Model for End-to-End Autonomous Driving</h3>

Bencheng Liao<sup>1,2</sup>, Shaoyu Chen<sup>2,3</sup>, Haoran Yin<sup>3</sup>, Bo Jiang<sup>2</sup>, Cheng Wang<sup>1,2</sup>, Sixu Yan<sup>2</sup>, Xinbang Zhang<sup>3</sup>, Xiangyu Li<sup>3</sup>, Ying Zhang<sup>3</sup>, Qian Zhang<sup>3</sup>, Xinggang Wang<sup>2 :email:</sup>

<sup>1</sup> Institute of Artificial Intelligence, HUST, <sup>2</sup> School of EIC, HUST, <sup>3</sup> Horizon Robotics

(<sup>:email:</sup>) corresponding author, xgwang@hust.edu.cn

Accepted to CVPR 2025 as Highlight!

</div>

News

Apr. 4th, 2025: DiffusionDrive is awarded as CVPR 2025 Highlight!
Feb. 27th, 2025: DiffusionDrive is accepted to CVPR 2025!
Jan. 18th, 2025: We release the initial version of code and weight on nuScenes, along with documentation and training/evaluation scripts. Please run git checkout nusc to use it.
Dec. 16th, 2024: We release the initial version of code and weight on NAVSIM, along with documentation and training/evaluation scripts.
Nov. 25th, 2024: We released our paper on Arxiv. Code/Models are coming soon. Please stay tuned! ☕️

Introduction
Qualitative Results on NAVSIM Navtest Split
Video Demo on Real-world Application
Getting Started
Contact
Acknowledgement
Citation

Introduction

Diffusion policy exhibits promising multimodal property and distributional expressivity in robotic field, while not ready for real-time end-to-end autonomous driving in more dynamic and open-world traffic scenes. To bridge this gap, we propose a novel truncated diffusion model, DiffusionDrive, for real-time end-to-end autonomous driving, which is much faster (10x reduction in diffusion denoising steps), more accurate (3.5 higher PDMS on NAVSIM), and more diverse (64% higher mode diversity score) than the vanilla diffusion policy. Without bells and whistles, DiffusionDrive achieves record-breaking 88.1 PDMS on NAVSIM benchmark with the same ResNet-34 backbone by directly learning from human demonstrations, while running at a real-time speed of 45 FPS.

<div align="center"><b>Truncated Diffusion Policy.</b> <img src="assets/truncated_diffusion_policy.png" /> <b>Pipeline of DiffusionDrive. DiffusionDrive is highly flexible to integrate with onboard sensor data and existing perception modules.</b> <img src="assets/pipeline.png" /> </div>

Qualitative Results on NAVSIM Navtest Split

<div align="center"> <b>Going straight with car-following and lane-changing behaviors.</b> <img src="assets/straight_0.png" /> <b>Going straight with diverse lane-changing behavior, which interacts with traffic light and stops at the stop line.</b> <img src="assets/straight_1.png" /> <b>Turning left with diverse lane-changing behavior, which interacts with surrounding agents.</b> <img src="assets/left_0.png" /> <b>Turning right with car-following and overtaking behaviors.</b> <img src="assets/right_0.png" /> </div>

Video Demo on Real-world Application

https://github.com/user-attachments/assets/bd2364f3-73fd-4c29-b8b2-ead11f78926d

Getting Started

Checkpoint

Results on NAVSIM

| Method | Model Size | Backbone | PDMS | Weight Download | | :---: | :---: | :---: | :---: | :---: | | DiffusionDrive | 60M | ResNet-34 | 88.1 | Hugging Face |

Results on nuScenes

| Method | Backbone | Weight | Log | L2 (m) 1s | L2 (m) 2s | L2 (m) 3s | L2 (m) Avg | Col. (%) 1s | Col. (%) 2s | Col. (%) 3s | Col. (%) Avg | | :---: | :---: | :---: | :---: | :---: | :---: | :---:| :---: | :---: | :---: | :---: | :---: | | DiffusionDrive | ResNet-50 | HF | Github | 0.27 | 0.54 | 0.90 |0.57 | 0.03 | 0.05 | 0.16 | 0.08 |

Contact

If you have any questions, please contact Bencheng Liao via email (bcliao@hust.edu.cn).

Acknowledgement

DiffusionDrive is greatly inspired by the following outstanding contributions to the open-source community: NAVSIM, Transfuser, Diffusion Policy, MapTR, VAD, SparseDrive.

Citation

If you find DiffusionDrive is useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.

 @article{diffusiondrive,
  title={DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving},
  author={Bencheng Liao and Shaoyu Chen and Haoran Yin and Bo Jiang and Cheng Wang and Sixu Yan and Xinbang Zhang and Xiangyu Li and Ying Zhang and Qian Zhang and Xinggang Wang},
  booktitle    = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
                  {CVPR} 2025, Nashville, TN, USA, June 11-15, 2025},
  pages        = {12037--12047},
  publisher    = {Computer Vision Foundation / {IEEE}},
  year         = {2025},
  url          = {https://openaccess.thecvf.com/content/CVPR2025/html/Liao\_DiffusionDrive\_Truncated\_Diffusion\_Model\_for\_End-to-End\_Autonomous\_Driving\_CVPR\_2025\_paper.html},
  doi          = {10.1109/CVPR52734.2025.01124}
}

DiffusionDrive

Install / Use

README