Imagine a game of Pictionary where based on the cue cards, you have to draw something that describes it. It’s not that difficult, but it now seems that Microsoft has managed to develop a bot and has taught it how to draw based on text descriptions. It also seems that it can go beyond the descriptions, adding in details that weren’t present.According to Microsoft, “The technology, which the researchers simply call the drawing bot, can generate images of everything from ordinary pastoral scenes, such as grazing livestock, to the absurd, such as a floating double-decker bus. Each image contains details that are absent from the text descriptions, indicating that this artificial intelligence contains an artificial imagination.”
Xiaodong He, a principal researcher and research manager in the Deep Learning Technology Center at Microsoft’s research lab adds, “These birds may not exist in the real world — they are just an aspect of our computer’s imagination of birds.” If this sounds familiar, it is because last year Google unveiled an AI of their own that they taught how to doodle, but it is clear that Microsoft’s efforts have taken it beyond the doodling stage.
In terms of the practical application of such technology, Microsoft envisions that it could be used by painters and interior designers, or perhaps used as a tool for voice-activated photo refinement (perhaps that’s the long-term game plan for Cortana Microsoft was talking about).
Filed in . Read more about AI (Artificial Intelligence) and Microsoft.