Microsoft develops AI Drawing Bot capable of sketching based on individual words

Microsoft has developed artificial intelligence capable of paying close attention to individual words when generating images from caption-like text descriptions. The technology, simply named The Drawing Bot, can generate imagery of everything from “ordinary pastoral scenes, such as grazing livestock, to the absurd, such as a floating double-decker bus.”

“If you go to Bing and you search for a bird, you get a bird picture. But here, the pictures are created by the computer, pixel by pixel, from scratch,” Xiaodong He, a principal researcher and research manager in the Deep Learning Technology Centre at Microsoft’s research lab in Washington, describes. “These birds may not exist in the real world – they are just an aspect of our computer’s imagination of birds.”

The Drawing Bot is the latest installation in a series of technological advancements made by Xiaodong and the rest of his team. Over the past 50 years, they have developed the CaptionBot which automatically writes photo captions as well as technology that answers questions humans ask about images, such as the location of an object within an image.

The development of image generation is particularly significant as it requires The Drawing Bot to imagine details that are not contained in the caption. “That means you need your machine learning algorithms running your artificial intelligence to imagine some missing parts of the images,” says Pengchuan Zhang, an associate researcher on the team.

Predicted uses for The Drawing Bot range from a sketch assistant for painters and interior designers, to a voice-activated tool for photo editing. With more computing power Xiaodong imagines the technology could generate animated films based on screenplays, automating and augmenting the work that animators do by removing some of the manual labour involved.