Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929446112460800 |
|---|---|
| author | Wang, Yixiao Tang, Chen Sun, Lingfeng Rossi, Simone Xie, Yichen Peng, Chensheng Hannagan, Thomas Sabatini, Stefano Poerio, Nicola Tomizuka, Masayoshi Zhan, Wei |
| author_facet | Wang, Yixiao Tang, Chen Sun, Lingfeng Rossi, Simone Xie, Yichen Peng, Chensheng Hannagan, Thomas Sabatini, Stefano Poerio, Nicola Tomizuka, Masayoshi Zhan, Wei |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00766 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation Wang, Yixiao Tang, Chen Sun, Lingfeng Rossi, Simone Xie, Yichen Peng, Chensheng Hannagan, Thomas Sabatini, Stefano Poerio, Nicola Tomizuka, Masayoshi Zhan, Wei Computer Vision and Pattern Recognition 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/. |
| title | Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.00766 |