Remember our good old friend, the GAN? It’s the type of AI algorithm that synthesizes art and realistic images by pitting two neural networks against each other. Here’s another thing it can do: remove photo-bombers from your pictures, sans other photo-editing software.
Researchers at the Max Planck Institute and CISPA Helmholtz Center developed a technique that uses two separate GANs to achieve the task. The first GAN uses what they call a “mask generator” to clumsily cover up the pixels of the target object until the “mask discriminator” can no longer recognize it. The second GAN uses an “in-painter” to turn the messy cover-up into something photorealistic, until the discriminator can no longer tell that it’s synthesized. The result? See for yourself above.
Why Meta’s latest large language model survived only three days online
Galactica was supposed to help scientists. Instead, it mindlessly spat out biased and incorrect nonsense.
DeepMind’s game-playing AI has beaten a 50-year-old record in computer science
The new version of AlphaZero discovered a faster way to do matrix multiplication, a core problem in computing that affects thousands of everyday computer tasks.
The White House just unveiled a new AI Bill of Rights
It's the first big step to hold AI to account.
Google’s new AI can hear a snippet of song—and then keep on playing
The technique, called AudioLM, generates naturalistic sounds without the need for human annotation.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.