Hacking Photography - one Picture at a time
Deepfakes have been a thing for a while now, and they’ve been used for fun, useful, but also malicious purposes. Samsung has now introduced yet another deepfake tool that turns a single still image into a creepily accurate video.
Samsung’s Megapixel portraits, or MegaPortraits, is able to create high-resolution human avatars. All it needs is a single portrait, and it doesn’t even have to be a photo – you can also turn paintings into moving portraits, for some extra creepiness.
With the rise in AI-generated imagery lately, creating fake images, even very realistic looking human faces is become more widespread and readily available than ever – especially thanks to services like This Person Does Not Exist – which uses NVIDIA tech that we’ve featured here before. To our eyes, it’s often almost impossible to tell what’s real and what’s not anymore.
But a new Chrome extension from V7 Labs wants to take the guesswork out of figuring out which faces on the web are fake and which are legit, and it does it with a claimed 99.28% accuracy. It’s designed to help rid us of misleading content and fake profiles for people who simply do not exist in the real world, as V7 Labs founder Alberto Rizzoli explains in a video published to Loom.
DxO’s PhotoLab has seen a lot of improvements over the years. Their latest iteration, PhotoLab 4 comes with some pretty impressive high ISO noise reduction along with a host of workflow speed and other features. These improvements allow you to customise the user interface and provide easier access to your more commonly used tools, as well as adding a few new ones.
Artificial intelligence keeps getting better. A group of scientists from China has developed an algorithm that can turn sketches into realistic portraits. It even works with pretty rough sketches, and the end results look very close to real photos of people.
We’ve already seen some AI software that can upsample low-res images. You know, CSI-style. Face Depixelizer is another AI-powered software, particularly focused on faces. It can take a pixelated, low-res photo and turn it into a realistic portrait. While the results are pretty impressive – the app doesn’t come without its quirks.
When AI-generated faces became more widespread and available, some people feared that these fake portraits could be misused. Well, their fears came true. On Friday, Facebook removed almost a thousand of fake profiles, pages, and groups that used photos generated by artificial intelligence. And according to the sources, all of them were used to push political, mainly right-wing campaigns.
Of course, I’m kidding, how can anybody get sick of dog pictures on Facebook?
Nvidia’s research teams have been doing some pretty crazy stuff with AI the last few years. This latest one is pretty funny from an amusement level standpoint but quite groundbreaking from a technical one. Nvidia’s GANimal AI lets you remap your pet’s “expression” onto other animals.
We’ve already seen that AI-generated faces can look so realistic that it’s sometimes difficult to distinguish them from real ones. And if you want to put a fake headshot to use, Generated Photos lets you choose from 100,000 AI-generated faces. They’re all free for download and you can use them whichever way you want. What’s more, many of them look so good that it’s hard to tell them apart from photos licensed by stock photo companies.
Deepfake has become a pretty hot topic in the world of visual AI over the last couple of years, and it’s come a very long way in a short amount of time. It’s an incredible and terrifying technology. And now Samsung has jumped on the bandwagon.
Researchers at the Samsung AI Center in Mosci and the Skolkovo Institute of Science and Technology have published a new paper detailing their new software that generates 3D animated heads from a still image. And while it’s not perfect, to be able to do this from a handful or even a single image is pretty mindblowing.
We’ve seen NVIDIA’s impressive content aware tool and noise removing tool. They have recently developed a generative adversarial network (GAN) which easily customizes styles of realistic faces and creates new faces. That’s right, these super-realistic faces you can see in the lead image are not real at all!
FIND THIS INTERESTING? SHARE IT WITH YOUR FRIENDS!