An advanced artificial intelligence (AI) technology has been developed that can extract three-dimensional (3D) spatial structure and object information within indoor environments using just a single ...

DCGCN decomposes the 3D point cloud data of a molecule into three components: atomic sequence, atomic connectivity, and a distance map. From its connectivity and distance information, DCGCN captures ...

A new, densely annotated 3D-text dataset called 3D-GRAND can help train embodied AI, like household robots, to connect language to 3D spaces. The study, led by University of Michigan researchers, was ...

This paper addresses the challenges in underwater 3D scene reconstruction and proposes an innovative Water-Adapted 3D Gaussian Splatting method, which effectively handles the geometric structure of ...

Apple has announced an interesting 3D AI model called Matrix3D that is able to reconstruct 3D objects and scenes from just a few 2D photos.

Nvidia’s new tool can turn 3D scenes into AI images Nvidia’s ‘AI Blueprint for 3D-guided generative AI’ combines Blender with a text-to-image generator.

Researchers at Georgia Tech have created a new three-dimensional (3D) acceleration framework that instantly transforms flat, two-dimensional photos into immersive 3D images. School of Computer Science ...

Fei-Fei Li's World Labs has announced its first project: an AI system that can generate video game-like, 3D scenes from a single image.