NVIDIA's new AI model quickly generates objects and characters for virtual worlds

NVIDIA is looking to take the sting out of creating virtual 3D worlds with a new artificial intelligence model. GET3D can generate characters, buildings, vehicles and other types of 3D objects, NVIDIA says. The model should be able to whip up shapes quickly too. The company notes that GET3D can generate around 20 objects per second using a single GPU.

Researchers trained the model using synthetic 2D images of 3D shapes taken from multiple angles. NVIDIA says it took just two days to feed around 1 million images into GET3D using A100 Tensor Core GPUs.

The model can create objects with “high-fidelity textures and complex geometric details,” NVIDIA’s Isha

→ Continue reading at Engadget

Similar Articles


Most Popular

Tyler Van Dyke’s rough week ends with him as a spectator

Miami Hurricanes quarterback Tyler Van Dyke has had a rough week. It began last Saturday night, when Van Dyke and the Miami Hurricanes faced...

Seeing more spiders around in western Washington? There's no need to fear

The arachnid curator at the Burke Museum says just about everything you think you know about spiders is wrong, and they aren't as scary...

Netflix Renews Deal with Millimages for Seasons 2, 3, 4 of Hit Series ‘Molang’ (EXCLUSIVE)

French kids entertainment company Millimages has announced it is renewing with Netflix for Seasons 2, 3 and 4 of its hit series “Molang”,...