GAIA-2: A Controllable Multi-View Generative World Model 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_ | 1866915213941407744 |
|---|---|
| author | Russell, Lloyd Hu, Anthony Bertoni, Lorenzo Fedoseev, George Shotton, Jamie Arani, Elahe Corrado, Gianluca |
| author_facet | Russell, Lloyd Hu, Anthony Bertoni, Lorenzo Fedoseev, George Shotton, Jamie Arani, Elahe Corrado, Gianluca |
| contents | Generative models offer a scalable and flexible paradigm for simulating complex environments, yet current approaches fall short in addressing the domain-specific requirements of autonomous driving - such as multi-agent interactions, fine-grained control, and multi-camera consistency. We introduce GAIA-2, Generative AI for Autonomy, a latent diffusion world model that unifies these capabilities within a single generative framework. GAIA-2 supports controllable video generation conditioned on a rich set of structured inputs: ego-vehicle dynamics, agent configurations, environmental factors, and road semantics. It generates high-resolution, spatiotemporally consistent multi-camera videos across geographically diverse driving environments (UK, US, Germany). The model integrates both structured conditioning and external latent embeddings (e.g., from a proprietary driving model) to facilitate flexible and semantically grounded scene synthesis. Through this integration, GAIA-2 enables scalable simulation of both common and rare driving scenarios, advancing the use of generative world models as a core tool in the development of autonomous systems. Videos are available at https://wayve.ai/thinking/gaia-2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20523 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving Russell, Lloyd Hu, Anthony Bertoni, Lorenzo Fedoseev, George Shotton, Jamie Arani, Elahe Corrado, Gianluca Computer Vision and Pattern Recognition Artificial Intelligence Robotics Generative models offer a scalable and flexible paradigm for simulating complex environments, yet current approaches fall short in addressing the domain-specific requirements of autonomous driving - such as multi-agent interactions, fine-grained control, and multi-camera consistency. We introduce GAIA-2, Generative AI for Autonomy, a latent diffusion world model that unifies these capabilities within a single generative framework. GAIA-2 supports controllable video generation conditioned on a rich set of structured inputs: ego-vehicle dynamics, agent configurations, environmental factors, and road semantics. It generates high-resolution, spatiotemporally consistent multi-camera videos across geographically diverse driving environments (UK, US, Germany). The model integrates both structured conditioning and external latent embeddings (e.g., from a proprietary driving model) to facilitate flexible and semantically grounded scene synthesis. Through this integration, GAIA-2 enables scalable simulation of both common and rare driving scenarios, advancing the use of generative world models as a core tool in the development of autonomous systems. Videos are available at https://wayve.ai/thinking/gaia-2. |
| title | GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2503.20523 |