December 22, 2018
-
Creepy AI can now create ‘100 per cent lifelike’ human faces from scratch
Artificial Intelligence is now able to create lifelike human faces from scratch. Can you tell who is real and who is not?
Can you tell which are real persons and which are fake persons? The pictures on the right are AI generated
Researchers at NVIDIA have been working on creating realistic looking human faces from only a few source photos for years. For many people it's difficult to tell the difference between one of the faces generated below and an actual human face, can you spot which is which?
The team at NVIDIA, released a paper on the subject, and explained they used Generative Adversarial Networks (GAN), to customise the realistic looking faces. The fake faces can be easily customised by using a method known as 'style transfer' that blends the characteristics of one image with another. The generator thinks of the image as a collection of three styles, known as coarse styles (pose, hair, face shape), middle styles (facial features and eyes) and fine styles (colour scheme). Animals, such as cats, and objects such as a bedroom can also be generated, using the same method.
The researchers created a grid to show the extent to which they could alter people's facial characteristics using only one source image.
One of the most fascinating aspects of this is GAN has only be around for four years. But, is it not yet perfect, there are giveaways that can indicate that you are looking at an AI image. For example the hair is very difficult to replicate, and as such, can often looked painted on, or slightly peculiar.
The advances in this technology also pose interesting ethical questions. Can people really trust pictorial evidence? What are the implications for governments or repressive regimes being able to use this technology for propaganda or to spread misinformation?
Earlier this year we revealed how Nvidia software uses AI and deep-learning algorithms to predict what a missing portion of a picture should look like and recreate it with incredible accuracy. All users need to do is click and drag over the area to be filled in and the image is instantly updated.
As well as restoring old physical photos that have been damaged, the technique could also be used to fix corrupted pixels or bad edits made to digital files. Graphics specialist Nvidia, based in Santa Clara, California trained its neural network using a variety of irregular shaped holes in images. The system then determined what was missing from each and filled in the gaps.
Extracted from: www.dailymail.co.uk
