An AI method enables the generation of sharp, high-quality 3D shapes that are closer to the quality of the best 2D image models. Previous approaches typically generated blurry or cartoonish 3D shapes.

The Marble model can generate 3D worlds, a major step toward what the AI leader calls ‘spatial intelligence.’ ...

Researchers at Nvidia Corp. closed out this year’s GTC 2024 conference today by unveiling a new, more powerful text-to-3D generative artificial intelligence model. It’s called LATTE3D, and it works by ...

Researchers at the University of North Carolina at Chapel Hill developed technology to calculate the 3D model of the human body and clothes from the image of one person without motion and to change ...

Nvidia Corp. today revealed that it has created a new deep learning application that can take a standard 2D image and transform it into an extremely realistic 3D model, one that can be visualized and ...

Researchers have for the first time managed to reproduce the asymmetries and fast-moving iron clumps of observed supernovae by complex computer simulations in all three dimensions. To this end they ...