Science & Technology

Microsoft Introduces AI With Sketching Capabilities

| January 20 , 2018 , 14:55 IST

Microsoft has a new 'drawing bot' that can create pictures, pixel by pixel, of objects based upon user description. According to a Microsoft Research's Blogpost, the new bot has "produced a nearly three-fold boost in image quality compared to the previous state-of-the-art technique for text-to-image generation," using an industry standard test.

Above image of a bird was produced by Microsoft's latest AI from a brief textual description of a yellow bird with black wings and a short beak resting on a branch. As pictured, there may or may not be such a bird in existence on earth.

That might be a rather humdrum example as the researchers say the AI can paint, from scratch, "everything from ordinary pastoral scenes, such as grazing livestock, to the absurd, such as a floating double-decker bus". The AI does in effect use its own imagination when filling in the gaps in a description of a scene.

Previous AIs would tend to lose too much detail, says Microsoft. For example, if described to draw a bird with a green crown, yellow wings and red belly a smudgy image would usually be generated, even though the same previous AI's could do simple bird drawings very well. Microsoft's new attentional GAN, or AttnGAN, is designed to improve drawing accuracy when given more textual detail - it has more focus and 'common sense' which is accrued in its training stages.

Application on this platform will be a treat for interior designer or Painter. it could work as their sketch assistant, or it could be a tool for photo refinement tool. With further development time and processing power, it is possible that the AI could go on to create animations based on storyboard descriptions, reducing human efforts.

ALSO READ - Sophia, World’s First Robot Citizen