Imagine using a black and white photo of your great grandparents to see what their facial expression looked like as they speak. That’s the kind of trick current technology can actually make possible. Using artificial intelligence and machine learning, companies only need a single picture to bring it to life, whether it’s someone’s photo or a painting like DaVinci’s Mona Lisa.
Samsung engineers in Moscow and Skolkovo Institute of Science and Technology have developed a new AI technique that can transform an image of you into an Animoji. It’s like a video with the face making speech expressions, except it wouldn’t exactly be your video, it would be your picture turned into a video. Get it? The more images you have for the person whose skills you want to animate, the better the result will be, as the computer will be able to take into account multiple angles, facial movements, and poses. The result is so sophisticated that in many cases, you won’t be able to tell the difference. To demonstrate the new software, the Samsung team shared a video showing fun applications like “living portraits,” in which images of celebrities like Marilyn Monroe and Salvador Dali are brought to life.
DataGrid, a Japanese start-up company based out of Kyoto University, have developed an AI system that is capable of smoothly and automatically creating high-quality and high-resolution (1024 x 1024) photorealistic models of entire people.
What if the person you were watching on TV was not an actual human?
Isn’t Deepfake AI risky?
Is AI going too far? Why is Deepfakes making people nervous?
The results of Deepfake AI are unbelievably amazing. However, we should not forget that this is the kind of feature that could put a dangerous weapon into the hands of people with malicious intentions. When people realized that scammers and people playing hoaxes used Photoshop to create fake images, we had to become more alert about what we considered proof. Luckily, there were many ways to detect whether an image was fake, even with the naked eye. However, deepfakes are different. Machine learning makes life more comfortable, but in this case, it makes fakery significantly easier. First thing, the software is widely and freely available. Second thing, you don’t need advanced skills to apply a face-swap, the software will do it for you.
Since AI and deep learning help create deepfakes, the tech also improves and becomes more convincing at an alarming rate. The system uses various facial expressions on top of the source image, turning a photo into a moving head. The AI doesn’t use voice, so you can’t use it to create a Trump video delivering a false declaration of war. However, the technology that might make something like that possible is also in the works. Imagine someone creating a deep fake video of you simply by stealing your profile picture. Just think if a robbery took place in any part of the world and the only suspect is you. There is video and photographic evidence of you committing the crime. But you didn’t do it. It turns out that one of your boss who actually committed the crime created fake CCTV images of you on his laptop. It’s horrible!
While the technology has its own fun applications, and sometimes very practical ones too, it has acquired a notorious status because in many cases it is being used to morph celebrity faces, famous personalities onto the bodies of others, on face of actors of pornographic films, and for creating fake controversial content. There are tons of explicit videos online, where celebrities’ faces have been grafted over someone else’s. In most countries, no laws deal with this kind of content yet, making it difficult to control. How will the government and courts deal with this new wave of fake images and videos?
The future is scary with this type of invention. You already can’t tell the difference between real and unreal. Practically everything you see, or hear, nowadays is scripted, Digitally Sampled, Stored, Duplicated, Synthesized, Morphed, CGI Green Screen, Chromakey Overlay, CGI Animation, Virtual Reality, Augmented Reality, Mixed Reality, Detailed Models, or Robotics.
One thing is for sure, the next 20 years going to be terrified or very excited. Obviously, there are some real benefits of creating these sorts of pictures – at least, from an economic standpoint. Websites and catalogs will no longer need to seek people’s permission to use their portraits in advertising material, or pay costly models — another job lost in the ongoing AI revolution.
According to people attached to this project, this technology can be used for a host of applications, including video games, film, and TV. It can also be used for applications which involved telepresence including video conferencing and multi-player games as well as in the special effects industry. But are they aware of the negative effects of this technology? We must need to understand that AI will be millions of time more intelligent than the entire human race.
How will we control it?
Should we implement rules to slow its inevitable spread? How will forensic science keep up with photos and videos that are 100% realistic? Are we living in scary times?
Talk to us in the comment box and just remember that seeing isn’t always believing anymore!