Nvidia has developed an artificial intelligence tool that allows developers to create 3D virtual worlds. Get3d is able to create characters, buildings, vehicles and other 3D objects. According to Nvidia, the tool can generate about twenty elements per second using a single GPU.

According to Nvidia A must tool that is developed by artificial intelligence lab in torontoContributing to “the vast virtual worlds that are being created by a growing number of companies”. Developers can populate virtual worlds faster with a variety of objects via Get3d, according to the company.

Get3d is trained using 2D graphics, and according to Nvidia, it creates 3D objects with “high-resolution textures and intricate geometric details.” The objects are in the form of a triangular grid, like a papier-mâché model with texture on top of it.

Based on a data set of 2D images of cars, Get3d can create an array of sedans, trucks, racing cars, and pickups, among other things. When you submit images of animals, the AI ​​tool can create foxes, rhinos, and bears, for example. The tool can also convert text into 3D objects. The larger and more diverse the data set, the more diverse and detailed the result, Nvidia states logically.

3D objects created in many graphics software applications, such as game engines, can be imported, allowing developers to edit and manipulate them further. In addition to games, Nvidia also sees applications for 3D objects created in robotics, architecture, and social media, among other things.