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
How to protect assets, buildings, and personal health?
In an unpredictable world, protection has become a strategic necessity—not just an option. Whether it's safeguarding finances, strengthening buildings, or focusing on personal health, long-term stability relies on proactive planning. True security is
AI Browser Comet Launches with Full Multitasking Support on iPad
Perplexity’s AI browser, Comet, has officially launched its iPad version, now fully compatible with iPadOS. The update introduces multi-window browsing, multitasking support, and deep integration with leading AI models like OpenAI and Anthropic, deli
Trace raises $3M to tackle enterprise AI agent adoption hurdles
Despite their potential, AI agents have struggled to gain traction in the enterprise. One emerging startup believes the core issue is a lack of context.Launched as part of Y Combinator’s 2025 summer cohort, Trace is a workflow orchestration startup d
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).
How to protect assets, buildings, and personal health?
In an unpredictable world, protection has become a strategic necessity—not just an option. Whether it's safeguarding finances, strengthening buildings, or focusing on personal health, long-term stability relies on proactive planning. True security is
AI Browser Comet Launches with Full Multitasking Support on iPad
Perplexity’s AI browser, Comet, has officially launched its iPad version, now fully compatible with iPadOS. The update introduces multi-window browsing, multitasking support, and deep integration with leading AI models like OpenAI and Anthropic, deli
Trace raises $3M to tackle enterprise AI agent adoption hurdles
Despite their potential, AI agents have struggled to gain traction in the enterprise. One emerging startup believes the core issue is a lack of context.Launched as part of Y Combinator’s 2025 summer cohort, Trace is a workflow orchestration startup d





Home






