“Living Portraits”: Creating Fake Images Now Made Easier than Before

Thank Samsung for that.

Moscow, Russia — Researchers at the Samsung AI Center developed a way to create moving portraits using only a small dataset. The dataset can be so small that even one photograph is enough to make a moving portrait — a “living portrait.”

Because they only need one source image, the researchers were able to animate paintings and famous portraits, with eerie results. Fyodor Dostoevsky—who died well before motion picture cameras became commercially available—moves and talks in black and white. The Mona Lisa silently moves her mouth and eyes, a slight smile on her face. Salvador Dali rants on, mustache twitching.

This technology far more exceeds than that of deepfakes, which only pastes faces over another face.

Do you think technology has gone too far on this one?

Via Vice

(Video Credit: Egor Zakharov/ YouTube)


Login to comment.




Email This Post to a Friend
"“Living Portraits”: Creating Fake Images Now Made Easier than Before"

Separate multiple emails with a comma. Limit 5.

 

Success! Your email has been sent!

close window
X

This website uses cookies.

This website uses cookies to improve user experience. By using this website you consent to all cookies in accordance with our Privacy Policy.

I agree
 
Learn More