Lyra 2.0: Explorable Generative 3D Worlds

Understand

Recent advances in video generation enable a new paradigm for 3D scene creation: generating camera-controlled videos that simulate scene walkthroughs, then lifting them to 3D via feed-forward reconstruction techniques.

• This generative reconstruction approach combines the visual fidelity and creative capacity of video models with 3D outputs ready for real-time rendering and simulation.
• Scaling to large, complex environments requires 3D-consistent video generation over long camera trajectories with large viewpoint changes and location revisits, a setting where current video models degrade quickly.
• Existing methods for long-horizon generation are fundamentally limited by two forms of degradation: spatial forgetting and temporal drifting.