ArrowArtboardCreated with Sketch.Title ChevronTitle ChevronIcon FacebookIcon LinkedinIcon Mail ContactPath LayerIcon MailPositive ArrowIcon Print
Japan-Update

New AI model fills in blank spots in photos

Japanese university's tech can also slightly modify facial features

Before and after: New software developed by a team at Japan's Waseda University can take an incomplete picture and then fill in the blanks. (Courtesy of professor Hiroshi Ishikawa)

TOKYO -- A new technology uses artificial intelligence to generate synthetic images that can pass as real.

The technology was developed by a team led by Hiroshi Ishikawa, a professor at Japan's Waseda University. It uses convolutional neural networks, a type of deep learning, to predict missing parts of images. The technology could be used in photo-editing apps. It can also be used to generate 3-D images from real 2-D images. 

Sponsored Content

About Sponsored Content This content was commissioned by Nikkei's Global Business Bureau.

Discover the all new Nikkei Asia app

  • Take your reading anywhere with offline reading functions
  • Never miss a story with breaking news alerts
  • Customize your reading experience

Nikkei Asian Review, now known as Nikkei Asia, will be the voice of the Asian Century.

Celebrate our next chapter
Free access for everyone - Sep. 30

Find out more