News

AI technique captures complexity of human faces to help create realistic photo edits

The ability to distil images to their most essential components and anticipate new scenes is what could drive computer vision and robotics forward

Half a century ago, we expected the future to hold sophisticated computers and robot helpers to slash the time we spend on work and household chores.

Yet, while we now have nearly unlimited knowledge at our fingertips, the level of automation that some predicted still hasn’t come to be. What happened?

It turns out that things are a little more complicated than we expected.

‘It’s taken us a surprisingly long time to come to terms with how complex the world is,’ says Jaakko Lehtinen, an associate professor of computer science at Aalto University and distinguished research scientist at computer graphics firm NVIDIA.

Unsupervised learning

Lehtinen’s work focuses on Artificial Intelligence techniques that create new, realistic images, simply by looking at examples. The method has not just helped speed up tasks, which in the past could take a skilled professional days or weeks, to a matter of seconds but eliminated the need for human eyes all together.

‘Doing this without human supervision is a building block of intelligence,’ Lehtinen explains. ‘Looking at a large collection of images, the algorithm distils the essence of what it sees into a recipe, which it uses to create new images that show the same, hard-to-pinpoint laws and rules.’

With colleagues at NVIDIA, the techniques have, for example, created pictures of non-existent faces that look so eerily real, you could swear they were in the last movie you saw. Most recently, they have made their way into New Portrait tool in Adobe Photoshop, which users around the world can use to easily change the gaze, smile or even age of real faces.

Toimittaja Katrina Jurvan hymyilevät kasvot on käsitelty kuvaan nykyistä vanhemmiksi. Hän on pukeutunut valkoiseen paitaan, kuvan tausta on musta.
Lehtinen and colleagues’ work has helped power Adobe Photoshop’s new Smart Portrait Tool. Thanks to close collaboration with Adobe, the technique moved from academic publication to the hands of users in just a couple years. Photo: Mikko Raskinen

Smarts for the real world

These are impressive achievements, but it’s easy to overlook the potential of this technology if we concentrate on image creation or manipulation. Lehtinen says that methods that learn to imagine what’s out there will be crucial to computer vision and robotics going forward.

‘To deal with a completely new environment, like your home or office, and all of the real-world scenarios that may occur there, a robot needs a really robust idea of what all kinds of different homes and offices look like. These techniques could finally help them deal with all that complexity.’

Watch our Way Out There episode to learn more!

This article will be published in the Aalto University Magazine issue 28 coming out in May.

  • Published:
  • Updated:
Share
URL copied!

Read more news

Camilla Inkeroinen ja Hanna Vanhanen
Aalto Magazine Published:

Researchers develop the perfect recycled fertilizer for forests - saves 88% of energy normally used but still not legal

Finnish forests are typically nourished with fertilisers containing energy-intensive nitrogen and phosphorous mined in Morocco. Researchers have now developed an ecological alternative with ingredients sourced from a waste processing plant. It is good for forests and the environment – but legislation has to change first.
Aalto University Magazinen suomenkielisiä ja englanninkielisiä numeroita pöydällä
Aalto Magazine Published:

Aalto University Magazine examines trust in the digital world, commerce and between people

In this issue’s articles, the theme is discussed by Aalto alumnus Mårten Mickos, the philosopher Esa Saarinen and Swappie co-founder Sami Marttinen.
Piirroskuva ihmisestä digimaailmassa, piirros: Sanni Wessman
Aalto Magazine Published:

The builders of digital trust

A society gone online needs encrypters, white hats and appropriately suspicious citizens.
Kuvituskuvassa mieshenkilö istuu näyttöruudun edessä, josta lähtee yhteyksiä erilaisiin laitteisin, ketjuun on merkitty kirjaimet VPN sekä lukkojen kuvia
Aalto Magazine Published:

Specialised networks to provide information security

We all know that any information shared on the internet is not necessarily private. However, specialised networks with mobile access would offer isolation from the internet, and therefore, better information security.