SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model
Guardat en:
| Publicat a: | The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings (2025), p. 1570-1580 |
|---|---|
| Autor principal: | |
| Altres autors: | , , , , , , , |
| Publicat: |
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
|
| Matèries: | |
| Accés en línia: | Citation/Abstract |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3247056732 | ||
| 003 | UK-CbPIL | ||
| 024 | 7 | |a 10.1109/CVPR52734.2025.00154 |2 doi | |
| 035 | |a 3247056732 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 228229 |2 nlm | ||
| 100 | 1 | |a Tan, Shuhan |u UT Austin | |
| 245 | 1 | |a SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model | |
| 260 | |b The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |c 2025 | ||
| 513 | |a Conference Proceedings | ||
| 520 | 3 | |a Conference Title: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Conference Start Date: 2025 June 10Conference End Date: 2025 June 17Conference Location: Nashville, TN, USAThe goal of traffic simulation is to augment a potentially limited amount of manually-driven miles that is available for testing and validation, with a much larger amount of simulated synthetic miles. The culmination of this vision would be a generative simulated city, where given a map of the city and an autonomous vehicle (AV) software stack, the simulator can seamlessly simulate the trip from point A to point B by populating the city around the AV and controlling all aspects of the scene, from animating the dynamic agents (e.g., vehicles, pedestrians) to controlling the traffic light states. We refer to this vision as CitySim, which requires an agglomeration of simulation technologies: scene generation to populate the initial scene, agent behavior modeling to animate the scene, occlusion reasoning, dynamic scene generation to seamlessly spawn and remove agents, and environment simulation for factors such as traffic lights. While some key technologies have been separately studied in various works, others such as dynamic scene generation and environment simulation have received less attention in the research community. We propose SceneDiffuser++, the first end-to-end generative world model trained on a single loss function capable of point A-to-B simulation on a city scale integrating all the requirements above. We demonstrate the city-scale traffic simulation capability of SceneDiffuser++ and study its superior realism under long simulation conditions. We evaluate the simulation quality on an augmented version of the Waymo Open Motion Dataset (WOMD) with larger map regions to support trip-level simulation. | |
| 653 | |a Pattern recognition | ||
| 653 | |a Simulation | ||
| 653 | |a Scene generation | ||
| 653 | |a Pedestrians | ||
| 653 | |a Computer vision | ||
| 653 | |a Traffic signals | ||
| 653 | |a Occlusion | ||
| 653 | |a Environment simulation | ||
| 700 | 1 | |a Lambert, John |u Waymo LLC | |
| 700 | 1 | |a Jeon, Hong |u Waymo LLC | |
| 700 | 1 | |a Kulshrestha, Sakshum |u Waymo LLC | |
| 700 | 1 | |a Bai, Yijing |u Waymo LLC | |
| 700 | 1 | |a Luo, Jing |u Waymo LLC | |
| 700 | 1 | |a Anguelov, Dragomir |u Waymo LLC | |
| 700 | 1 | |a Tan, Mingxing |u Waymo LLC | |
| 700 | 1 | |a Jiang, Chiyu Max |u Waymo LLC | |
| 773 | 0 | |t The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings |g (2025), p. 1570-1580 | |
| 786 | 0 | |d ProQuest |t Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3247056732/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch |