Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation
This work addresses computational efficiency for autonomous driving applications, representing an incremental improvement over existing diffusion model methods.
The paper tackles the challenges of inefficient inference and high computational demands in diffusion models for joint trajectory prediction and controllable generation in autonomous driving, introducing Optimal Gaussian Diffusion and Estimated Clean Manifold Guidance to streamline the process and achieve superior performance on the Argoverse 2 dataset.
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/.