Imagine that you have only one photo of the kitchen, and a computer based on it is able to create a three-dimensional video.
This is precisely why GAUDI was created, a new system based on artificial intelligence, capable of generating images of three-dimensional spaces from an ordinary image and a description given by text.
The project is still at an early stage and will have to develop in the coming years.
Its name is given in honor of the Catalan architect Antonio Gaudí, responsible for such iconic works in Barcelona as Sagrada Familia in Park Guell.
Based on a simple photograph, you can create moving visual images of spaces, as if video was filmed indoors.
Given the command to “go to the kitchen”, based on a photo, GAUDI can generate different routes to build a visual trajectory.
GAUDI uses a scalable two-stage approach. First, the system is responsible for learning to represent the environment appropriate for different camera angles. The distribution of these representations is then modeled in space.
The project is still at an early stage, so the quality of the video is still quite low resolution. But already now you can get an idea about the technology and its capabilities.
Of course, this only reinforces the rumors that Apple is seriously working on virtual reality devices.
This is a fairly specialized topic, but if you are interested in learning more about the project, you can see its development on the official Apple page at Github.
More on the topic:
The post Apple introduced GAUDI, an artificial intelligence capable of creating 3D scenes from a single photo and description appeared first on Gamingsym.