RESEARCH PAPER

GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving

Lloyd Russell; Anthony Hu; Lorenzo Bertoni; George Fedoseev; Jamie Shotton; Elahe Arani; Gianluca Corrado

Classification

View four quadrants
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. GAIA-2 is an autonomous-driving surround-video world simulator conditioned on supplied motion, camera and agent information. It predicts video latents and supports rollout/editing, but does not predict executable driving actions. The driving-specific simulator should not be grouped with general pretrained backbones. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX