NVIDIA Unveils Lyra 2.0, Creating Expansive 3D Scenes from Single Images

On April 16, 2026, NVIDIA's research team officially launched Lyra2.0, a 3D scene generation system. This technology constructs expansive, highly coherent virtual environments from a single photograph, effectively solving the problem of image distortion over long camera paths. With the growing demand for embodied AI training, Lyra2.0 represents a significant breakthrough in AI's ability to understand 3D space and simulate environments in real time.
Technically, Lyra2.0 can generate 3D environments extending up to 90 meters from a single image. To combat the spatial distortion and error accumulation caused by "forgetting" in traditional video models, researchers implemented two key innovations. The system stores 3D geometry data for each frame in real time, ensuring environmental consistency when the camera revisits previous locations. It also trains on defective output data, enabling the model to learn self-correction. Benchmark tests show Lyra2.0 outperforms six competing models, including GEN3C and Yume-1.5, in image quality and camera control, while its fast version boosts generation efficiency by 13 times.
Lyra2.0 now integrates seamlessly with physics engines like Nvidia Isaac Sim, allowing generated 3D scenes to be exported directly as mesh models. This closed-loop workflow enables robots to conduct efficient simulation training within AI-generated environments, drastically reducing the need for large-scale real-world 3D data collection. Although currently limited to static scenes, Lyra2.0's advancements in generation scale and stability provide a more robust and imaginative infrastructure for advancing physical perception in autonomous driving and general-purpose robots (AGI).
Related article
Indian Tech Tycoon Invests $30M in AI Rival to Microsoft Office
Serial entrepreneur Bhavin Turakhia is investing $30 million of his own capital, betting that the enterprise AI sector still has room for new players. His latest startup, Neo, operates on a core belief: legacy workplace software cannot simply be patc
Former OpenAI Chief Scientist Ilya’s SSI Unveils First Model
AI has achieved another major milestone. Following his departure from OpenAI, former chief scientist Ilya Sutskever established Safe Superintelligence Inc. (SSI), which has recently unveiled details regarding its inaugural model. Reports from oversea
Lovable Leads Atech's Seed Round as AI Ambient Coding Officially Enters the Hardware Field
On May 14, 2026, AI application development platform Lovable announced its participation in the $800,000 seed funding round for Danish hardware startup Atech. Led by Lovable, the round attracted top-tier venture capital firms including the a16z Scout
Related Special Topic Recommendations
Comments (0)
0/500

On April 16, 2026, NVIDIA's research team officially launched Lyra2.0, a 3D scene generation system. This technology constructs expansive, highly coherent virtual environments from a single photograph, effectively solving the problem of image distortion over long camera paths. With the growing demand for embodied AI training, Lyra2.0 represents a significant breakthrough in AI's ability to understand 3D space and simulate environments in real time.
Technically, Lyra2.0 can generate 3D environments extending up to 90 meters from a single image. To combat the spatial distortion and error accumulation caused by "forgetting" in traditional video models, researchers implemented two key innovations. The system stores 3D geometry data for each frame in real time, ensuring environmental consistency when the camera revisits previous locations. It also trains on defective output data, enabling the model to learn self-correction. Benchmark tests show Lyra2.0 outperforms six competing models, including GEN3C and Yume-1.5, in image quality and camera control, while its fast version boosts generation efficiency by 13 times.
Lyra2.0 now integrates seamlessly with physics engines like Nvidia Isaac Sim, allowing generated 3D scenes to be exported directly as mesh models. This closed-loop workflow enables robots to conduct efficient simulation training within AI-generated environments, drastically reducing the need for large-scale real-world 3D data collection. Although currently limited to static scenes, Lyra2.0's advancements in generation scale and stability provide a more robust and imaginative infrastructure for advancing physical perception in autonomous driving and general-purpose robots (AGI).
Indian Tech Tycoon Invests $30M in AI Rival to Microsoft Office
Serial entrepreneur Bhavin Turakhia is investing $30 million of his own capital, betting that the enterprise AI sector still has room for new players. His latest startup, Neo, operates on a core belief: legacy workplace software cannot simply be patc
Former OpenAI Chief Scientist Ilya’s SSI Unveils First Model
AI has achieved another major milestone. Following his departure from OpenAI, former chief scientist Ilya Sutskever established Safe Superintelligence Inc. (SSI), which has recently unveiled details regarding its inaugural model. Reports from oversea
Lovable Leads Atech's Seed Round as AI Ambient Coding Officially Enters the Hardware Field
On May 14, 2026, AI application development platform Lovable announced its participation in the $800,000 seed funding round for Danish hardware startup Atech. Led by Lovable, the round attracted top-tier venture capital firms including the a16z Scout





Home






