A programmer created an algorithmically-generated face, and then made the network slowly forget what its own face looked like.
The result, a piece of video art titled “What I saw before the darkness,” is an eerie time-lapse view of the inside of a demented AI’s mind as its artificial neurons are switched off, one by one, HAL 9000 style. Read More
Tag Archives: Image Recognition
Cameras That Can See Through Walls!
50 Famous Artists Brought to Life With AI
I’m working on a longer article about democratizing AI for artists, but in the process of writing that article, I started using Runway ML and Jason Antic’s deep learning project DeOldify to colorize old black-and-white photos of artists – I couldn’t stop. So I decided to share an “eye candy” article as a preview of my longer piece.
When I was growing up, artists, and particularly twentieth century artists, were my heroes. There is something about only ever having seen many of them in black and white that makes them feel mythical and distant. Likewise, something magical happens when you add color to the photo. These icons turn into regular people who you might share a pizza or beer with.
That distance begins to collapse a bit and they come to life. Read More
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Several recent works have shown how highly realistic human head images can be obtained by training convolutional neural networks to generate them. In order to create a personalized talking head model, these works require training on a large dataset of images of a single person. However, in many practical scenarios, such personalized talking head models need to be learned from a few image views of a person, potentially even a single image. Here, we present a system with such few-shot capability. It performs lengthy meta-learning on a large dataset of videos, and after that is able to frame few- and one-shot learning of neural talking head models of previously unseen people as adversarial training problems with high capacity generators and discriminators. Crucially, the system is able to initialize the parameters of both the generator and the discriminator in a person-specific way, so that training can be based on just a few images and done quickly, despite the need to tune tens of millions of parameters. We show that such an approach is able to learn highly realistic and personalized talking head models of new people and even portrait paintings. Read More
Mona Lisa frown: Machine learning brings old paintings and photos to life
Machine learning researchers have produced a system that can recreate lifelike motion from just a single frame of a person’s face, opening up the possibility of animating not just photos but also paintings. It’s not perfect, but when it works, it is — like much AI work these days — eerie and fascinating.
The model is documented in a paper published by Samsung AI Center, which you can read here on Arxiv. It’s a new method of applying facial landmarks on a source face — any talking head will do — to the facial data of a target face, making the target face do what the source face does. Read More
How computers learn to recognize objects instantly
These Cameras Can Spot Shoplifters Even Before They Steal
It’s watching, and knows a crime is about to take place before it happens. Read More
Rick's Cafe AI 