NVIDIA said on the model of artificial intelligence GET3D, which will facilitate the work of creators of virtual 3D worlds. The algorithm quickly generates people, buildings, vehicles and many other types of 3D objects. A GPU, the company said, allows GET3D to generate up to 20 objects per second.
Image source: blogs.nvidia.com
–
–
–
NVIDIA engineers trained AI on flat projections of three-dimensional objects made from different angles. The training was done on the A100 accelerators: it took only two days to load a million samples into GET3D. The system generates objects in the format of a standard triangular polygon mesh with high resolution textures. The technology is aimed at creators of 3D worlds, so you can export objects in formats compatible with game engines, 3D modeling, and movie rendering tools. This can really make it easier for developers to create metaverse games and applications – the system will also come in handy in robotics and architecture.
The algorithm distinguishes the nuances between similar objects: from vehicles it can generate sedans, trucks, racing cars and vans, from the animal category it creates images of foxes, rhinos, horses and bears – the set expands as you learn. NVIDIA also talked about the StyleGAN-NADA auxiliary AI model, which allows you to change the styles of objects: burn a car, transform a building into a haunted house or give the color of the tiger to any animal. The company will train future versions of the GET3D system on real objects and not artificially created models.
–
If you notice an error, select it with the mouse and press CTRL + ENTER.
–
