Nvidia Nvidia on Tuesday is debuting new research into 3D rendering that could one day make it easier for graphic artists, architects, and other creators to quickly build 3D models out of 2D images.

Unique3D predicts the shape of a subject from a photo taken from one direction by applying a 2D diffusion model, and can generate a 3D mesh model relatively quickly.

In a blog post and papers, Facebook highlights a pair of AI models that can convert 2D objects into 3D shapes with high accuracy.

Researchers at Microsoft have developed an AI model that converts 2D images into 3D shapes. They say it's superior to previous techniques.

Turning still 2D photos into 3D rendered mesh models is not a quick or particularly easy task, but perhaps not for long.