NVIDIA Neuralangelo is an all-new AI model capable of transforming 2D video clips into detailed 3D structures, whether it be of sculptures, buildings, or even a skyline. Previous methods were not able to translate the textures of complex materials, but Neuralangelo’s high-fidelity can reconstruct roof shingles, panes of glass, smooth marble and more.
Neuralangelo accomplishes this by adopting instant neural graphics primitives, or the technology behind NVIDIA Instant NeRF. Put simply, the AI model can use a 2D video of an object or scene filmed from various angles, and then select several frames that capture different viewpoints to get a sense of depth, size as well as shape. After determining the camera position of each frame, Neuralangelo’s AI creates a rough 3D representation of the scene. It then optimizes the render to refine the details and the final result is a 3D object that can be used in VR applications or robotics development.
- FX506HF-ES51
- SUPERCHARGED RTX GRAPHICS - Gameplay graphics are silky smooth with the NVIDIA GeForce RTX 2050 4GB GDDR6 at 70W with Dynamic Boost.
- READY FOR ANYTHING - Use your gaming laptop to stream and multitask with ease thanks to an Intel Core i5-11400H with 12M Cache, up to 4.5 GHz, 6 cores...
The 3D reconstruction capabilities Neuralangelo offers will be a huge benefit to creators, helping them recreate the real world in the digital world. This tool will eventually enable developers to import detailed objects — whether small statues or massive buildings — into virtual environments for video games or industrial digital twins,” said Ming-Yu Liu, senior director of research and co-author on the paper.
