NVIDIA · 2026-04-15 · major
Lyra 2.0 — NVIDIA's Explorable Generative 3D World Framework
NVIDIA Spatial Intelligence Lab releases Lyra 2.0: generates persistent, explorable 3D worlds via camera-controlled video diffusion, then lifts them to Gaussian Splats exportable to Isaac Sim. Apache 2.0.
NVIDIA's open-source framework for generating interactive 3D worlds — walk through, explore, export to Isaac Sim.
Key specs
| GitHub stars | 889 |
|---|---|
| Training data | synthetic from video diffusion |
What is it?
Lyra 2.0 is NVIDIA Spatial Intelligence Lab's framework for creating large, explorable 3D environments. Give it a text prompt or image and a camera trajectory; it generates a long consistent video walkthrough, reconstructs 3D Gaussian Splats from it, and serves an interactive scene you can navigate and export to real-time rendering engines or physics simulators.
How does it work?
The system tackles two core failure modes in long-horizon generation. Spatial forgetting — where the model hallucinates previously-seen regions — is addressed by maintaining per-frame 3D geometry and routing information via dense correspondences to relevant past frames, rather than regenerating from scratch. Temporal drifting — where small synthesis errors compound over time — is fixed through self-augmented training that exposes the model to its own degraded outputs so it learns to correct drift rather than propagate it.
Why does it matter?
Generating realistic 3D training environments without real-world scanning data is a bottleneck for robotics and embodied AI research. Lyra 2.0 exports 3D Gaussians directly into NVIDIA Isaac Sim, enabling synthetic data pipelines for robot training at scale. Apache 2.0 makes it commercially usable.
Who is it for?
Robotics researchers, embodied AI developers, 3D graphics practitioners.
Try it
git clone https://github.com/nv-tlabs/lyra