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.
- Chris Brooks has spent a decade rediscovering his family's 100-year-old printing press
- Spanish artist Ignasi Monreal firmly places classical painting in the now
- Kai Tang on how book design is timeless and therefore “more valuable”
- Tim Schutsky turns snow globes and scuffed-up trainers into scenes worth a second glance
- Champagne Nicko's illustrations feature characters in perpetual party mode
- Pablo Amargo on his simple and humorous illustrations for The New York Times
- Get ready for 230 new emojis to confuse your mum with
- Netflix rolls out brand new ident for all its original material
- David Rothenberg discusses his unique portraits of the passengers of planes
- Photographer Nick Turpin captures cars bathed in the lights of Piccadilly Circus
- Byun Young Geun likens illustration to “looking into a mirror”
- Naranjo-Etxeberria designs an identity aiming to cause impact at first glance