Take the pledge to vote

For a better tommorow#AajSawaroApnaKal
  • I agree to receive emails from News18

  • I promise to vote in this year's elections no matter what the odds are.
  • Please check above checkbox.

    SUBMIT

Thank you for
taking the pledge

Vote responsibly as each vote counts
and makes a diffrence

Disclaimer:

Issued in public interest by HDFC Life. HDFC Life Insurance Company Limited (Formerly HDFC Standard Life Insurance Company Limited) (“HDFC Life”). CIN: L65110MH2000PLC128245, IRDAI Reg. No. 101 . The name/letters "HDFC" in the name/logo of the company belongs to Housing Development Finance Corporation Limited ("HDFC Limited") and is used by HDFC Life under an agreement entered into with HDFC Limited. ARN EU/04/19/13618
LIVE TV DownloadNews18 App
News18 English
»
1-min read

Mona Lisa Talking: New Deepfake Video Makes Da Vinci's Classic Speak, Twitter Says 'Cool but Creepy'

It means that now, Deepfakes could even be created with still images instead of videos and that opens up a world of problems.

News18.com

Updated:May 26, 2019, 11:36 AM IST
facebookTwitterskypewhatsapp
Mona Lisa Talking: New Deepfake Video Makes Da Vinci's Classic Speak, Twitter Says 'Cool but Creepy'
Image credit: YouTube
Loading...

You've seen Mona Lisa smile. Now watch her speak. Researchers at the Samsung AI Research Centre in Moscow have come up with a study in which they managed to use Deepfake to create a video in which they made they Mona Lisa talk.

In a paper titled "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models," researchers have used a single image to create a Deepfake video of Leonardo Da Vinci's famous "Mona Lisa" painting. In the video, the woman in the painting could be seen talking, reaffirming once more that we have only just reached the tip of the iceburg in terms of Deepfake technology. The researchers used other still images such as those of Salvadore Dali, Fyodor Dostoyevsky and a print of "The Girl with the Pearl Earring".

According to a report in Motherboard, the researchers ran several videos of talking heads through "deep convolutional networks" to create the simulated movements out of the still image. While the videos are still not of the best quality and can easily be identified as Deepfakes, the implications of the study are disturbing. It means that now, Deepfakes could even be created with still images instead of videos and that opens up a world of problems.

Deepfakes are essentially morphed videos that realistically superimpose a person's face and body on videos that did not originally contain them. The system is already in use by a vast network of publishers and proprietors of fake news and pornography.

The video of Mona Lisa talking turned several heads on Twitter with some referring to it as "cool" while others called it "scary". Some found it both.

Watch the full results of the study here.

Read full article
Loading...
Next Story
Next Story

Also Watch

facebookTwitterskypewhatsapp

Live TV

Loading...
Countdown To Elections Results
  • 01 d
  • 12 h
  • 38 m
  • 09 s
To Assembly Elections 2018 Results