By decoupling scene state from camera viewpoint, GeoState makes 3D world predictions more accurate and generalizable—the same predicted scene can be rendered from different camera angles without retraining.
GeoState is a 3D world modeling approach that separates scene geometry from camera viewpoint by learning view-decoupled state representations. It uses a scene tokenizer to aggregate multi-view geometry features into a unified state, then predicts future states with an autoregressive model while handling camera motion separately.