Klicks
99Ranked in AIForest
Wird geladen...
Turn a single image or video into a persistent 3D world that can be explored endlessly, without the AI “forgetting” areas it has already visited. The generated scenes can be easily exported as Gaussian Splats or meshes directly into NVIDIA Isaac Sim for robotic simulation
Ranked in AIForest
Directory views
Sonstige
Computer Vision & Image Processing, Other
Lyra 2.0 Nvidia is a spatial AI tool that transforms a single image or video into an expansive 3D environment. Unlike standard generators, it features persistent memory, meaning it retains the layout of areas already visited during exploration. This allows for the creation of consistent, large-scale digital worlds that do not shift or change as the user moves through them.
The tool supports exporting generated scenes as either Gaussian Splats or 3D meshes. These formats are specifically optimized for integration into NVIDIA Isaac Sim. This makes it a valuable resource for robotics researchers and developers who need to quickly generate complex, realistic environments for testing autonomous agents and robotic simulations without manual environment building.
Einige Tool-Beschreibungen können auf Englisch erscheinen, wenn die automatische Übersetzung nicht verfügbar ist.