New AI technology under development at Microsoft is programmed to pay close attention to individual words when generating images from caption-like text descriptions.
This focus produced a nearly three-fold boost in image quality compared to the previous technique for text-to-image generation.
The technology, which the researchers call the drawing bot, can generate images of anything.
Each image contains details that are absent from the text descriptions, indicating the AI contains an artificial imagination.
The drawing bot closes a research circle around the intersection of computer vision and natural language processing.