English

Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation

Computer Vision and Pattern Recognition 2024-08-02 v1

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 TT 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/.

Keywords

Cite

@article{arxiv.2408.00766,
  title  = {Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation},
  author = {Yixiao Wang and Chen Tang and Lingfeng Sun and Simone Rossi and Yichen Xie and Chensheng Peng and Thomas Hannagan and Stefano Sabatini and Nicola Poerio and Masayoshi Tomizuka and Wei Zhan},
  journal= {arXiv preprint arXiv:2408.00766},
  year   = {2024}
}

Comments

30 pages, 20 figures, Accepted to ECCV 2024

R2 v1 2026-06-28T18:01:10.362Z