Nvidia to Create 3D Worlds in Metaverse with AI Modeling App Called GET3D
If you have watched the NYSE last month you know one of the tech stocks that has been taking a bit of a beating was Nvidia. Now things have turned around with the newest product release they announced on engadget.com this week. And it looks like a lot more Metaverse is headed our way.
NVIDIA is looking to take the sting out of creating virtual 3D worlds with a new AI 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 Salian wrote in a blog post. The shapes GET3D makes “are in the form of a triangle mesh, like a papier-mâché model, covered with a textured material,” Salian added.
As many of us may not yet be members of the metaverse or even the 3D gaming world we have included a video below to highlight part of NVIDIA’s recent advancements with AI.
It’s beginning to feel like we are a generation or two away from people living life in the digital universe rather than the real world. A bold statement perhaps but that is the goal of these corporations, particularly Meta. Their future depends on better 3D generators and a bigger more attractive digital universe. NVIDIA’s new AI is producing just that.
read more at engadget.com