Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation

Yixiao Wang, Chen Tang, Lingfeng Sun, Simone Rossi, Yichen Xie, Chensheng Peng, Thomas Hannagan, Stefano Sabatini, Nicola Poerio, Masayoshi Tomizuka, Wei Zhan

ECCV 2024

doi:10.1007/978-3-031-73397-0_19 /eccv/2024/wang2024eccv-optimizing/

Abstract

Diffusion models are promising for joint trajectory prediction and controllable generation in autonomous driving, but they face challenges of inefficient inference steps and high computational demands. To tackle these challenges, we introduce Optimal Gaussian Diffusion (OGD) and Estimated Clean Manifold (ECM) Guidance. OGD optimizes the prior distribution for a small diffusion time T and starts the reverse diffusion process from it. ECM directly injects guidance gradients to the estimated clean manifold, eliminating extensive gradient backpropagation throughout the network. Our methodology streamlines the generative process, enabling practical applications with reduced computational overhead. Experimental validation on the large-scale Argoverse 2 dataset demonstrates our approach’s superior performance, offering a viable solution for computationally efficient, high-quality joint trajectory prediction and controllable generation for autonomous driving. Our project webpage is at https://yixiaowang7.github.io/OptTrajDiff_ Page/

PDF ECCV Semantic Scholar

Cite

Text

Wang et al. "Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73397-0_19

Markdown

[Wang et al. "Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/wang2024eccv-optimizing/) doi:10.1007/978-3-031-73397-0_19

BibTeX

@inproceedings{wang2024eccv-optimizing,
  title     = {{Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation}},
  author    = {Wang, Yixiao and Tang, Chen and Sun, Lingfeng and Rossi, Simone and Xie, Yichen and Peng, Chensheng and Hannagan, Thomas and Sabatini, Stefano and Poerio, Nicola and Tomizuka, Masayoshi and Zhan, Wei},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2024},
  doi       = {10.1007/978-3-031-73397-0_19},
  url       = {https://mlanthology.org/eccv/2024/wang2024eccv-optimizing/}
}