HybridWorldSim: A Scalable and Controllable High-fidelity Simulator for Autonomous Driving
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911298770436096 |
|---|---|
| author | Li, Qiang Jiang, Yingwenqi Li, Tuoxi Chen, Duyu Feng, Xiang Ao, Yucheng Liu, Shangyue Yu, Xingchen Cai, Youcheng Liu, Yumeng Ma, Yuexin Hu, Xin Liu, Li Zhang, Yu Xu, Linkun Gao, Bingtao Wang, Xueyuan Zhou, Shuchang Liu, Xianming Liu, Ligang |
| author_facet | Li, Qiang Jiang, Yingwenqi Li, Tuoxi Chen, Duyu Feng, Xiang Ao, Yucheng Liu, Shangyue Yu, Xingchen Cai, Youcheng Liu, Yumeng Ma, Yuexin Hu, Xin Liu, Li Zhang, Yu Xu, Linkun Gao, Bingtao Wang, Xueyuan Zhou, Shuchang Liu, Xianming Liu, Ligang |
| contents | Realistic and controllable simulation is critical for advancing end-to-end autonomous driving, yet existing approaches often struggle to support novel view synthesis under large viewpoint changes or to ensure geometric consistency. We introduce HybridWorldSim, a hybrid simulation framework that integrates multi-traversal neural reconstruction for static backgrounds with generative modeling for dynamic agents. This unified design addresses key limitations of previous methods, enabling the creation of diverse and high-fidelity driving scenarios with reliable visual and spatial consistency. To facilitate robust benchmarking, we further release a new multi-traversal dataset MIRROR that captures a wide range of routes and environmental conditions across different cities. Extensive experiments demonstrate that HybridWorldSim surpasses previous state-of-the-art methods, providing a practical and scalable solution for high-fidelity simulation and a valuable resource for research and development in autonomous driving. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22187 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HybridWorldSim: A Scalable and Controllable High-fidelity Simulator for Autonomous Driving Li, Qiang Jiang, Yingwenqi Li, Tuoxi Chen, Duyu Feng, Xiang Ao, Yucheng Liu, Shangyue Yu, Xingchen Cai, Youcheng Liu, Yumeng Ma, Yuexin Hu, Xin Liu, Li Zhang, Yu Xu, Linkun Gao, Bingtao Wang, Xueyuan Zhou, Shuchang Liu, Xianming Liu, Ligang Computer Vision and Pattern Recognition Robotics Realistic and controllable simulation is critical for advancing end-to-end autonomous driving, yet existing approaches often struggle to support novel view synthesis under large viewpoint changes or to ensure geometric consistency. We introduce HybridWorldSim, a hybrid simulation framework that integrates multi-traversal neural reconstruction for static backgrounds with generative modeling for dynamic agents. This unified design addresses key limitations of previous methods, enabling the creation of diverse and high-fidelity driving scenarios with reliable visual and spatial consistency. To facilitate robust benchmarking, we further release a new multi-traversal dataset MIRROR that captures a wide range of routes and environmental conditions across different cities. Extensive experiments demonstrate that HybridWorldSim surpasses previous state-of-the-art methods, providing a practical and scalable solution for high-fidelity simulation and a valuable resource for research and development in autonomous driving. |
| title | HybridWorldSim: A Scalable and Controllable High-fidelity Simulator for Autonomous Driving |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2511.22187 |