DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving
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_ | 1866916430484602880 |
|---|---|
| author | Wang, Sheng Sun, Ge Ma, Fulong Hu, Tianshuai Qin, Qiang Song, Yongkang Zhu, Lei Liang, Junwei |
| author_facet | Wang, Sheng Sun, Ge Ma, Fulong Hu, Tianshuai Qin, Qiang Song, Yongkang Zhu, Lei Liang, Junwei |
| contents | Evaluating and training autonomous driving systems require diverse and scalable corner cases. However, most existing scene generation methods lack controllability, accuracy, and versatility, resulting in unsatisfactory generation results. Inspired by DragGAN in image generation, we propose DragTraffic, a generalized, interactive, and controllable traffic scene generation framework based on conditional diffusion. DragTraffic enables non-experts to generate a variety of realistic driving scenarios for different types of traffic agents through an adaptive mixture expert architecture. We employ a regression model to provide a general initial solution and a refinement process based on the conditional diffusion model to ensure diversity. User-customized context is introduced through cross-attention to ensure high controllability. Experiments on a real-world driving dataset show that DragTraffic outperforms existing methods in terms of authenticity, diversity, and freedom. Demo videos and code are available at https://chantsss.github.io/Dragtraffic/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12624 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving Wang, Sheng Sun, Ge Ma, Fulong Hu, Tianshuai Qin, Qiang Song, Yongkang Zhu, Lei Liang, Junwei Robotics Computer Vision and Pattern Recognition Evaluating and training autonomous driving systems require diverse and scalable corner cases. However, most existing scene generation methods lack controllability, accuracy, and versatility, resulting in unsatisfactory generation results. Inspired by DragGAN in image generation, we propose DragTraffic, a generalized, interactive, and controllable traffic scene generation framework based on conditional diffusion. DragTraffic enables non-experts to generate a variety of realistic driving scenarios for different types of traffic agents through an adaptive mixture expert architecture. We employ a regression model to provide a general initial solution and a refinement process based on the conditional diffusion model to ensure diversity. User-customized context is introduced through cross-attention to ensure high controllability. Experiments on a real-world driving dataset show that DragTraffic outperforms existing methods in terms of authenticity, diversity, and freedom. Demo videos and code are available at https://chantsss.github.io/Dragtraffic/. |
| title | DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.12624 |