10 Posts

Animation showing image-to-image style transfer — mapping process

AI With a Sense of Style: Style Transfer Method Produces Consistent Output in Successive Frames

The process known as image-to-image style transfer — mapping, say, the character of a painting’s brushstrokes onto a photo — can render inconsistent results. When they apply the styles of different artists to the same target
Examples of image generators using GANsformer

Attention for Image Generation: Combining GANs and transformers for more believable images.

Attention quantifies how each part of one input affects the various parts of another. Researchers added a step that reverses this comparison to produce more convincing images.
Detection of a digitally altered image of a frog holding a violin

Fighting Fakes: Six algorithms that help news sites spot deepfakes

A supergroup of machine learning models flags manipulated photos. Jigsaw, a tech incubator owned by Alphabet, released a system that detects digitally altered images.
Tree farm dataset

Representing the Underrepresented: Many important AI datasets contain bias.

Some of deep learning’s bedrock datasets came under scrutiny as researchers combed them for built-in biases. Researchers found that popular datasets impart biases against socially marginalized groups to trained models due to the ways the datasets were compiled, labeled, and used.
Examples of AI generated images

GANs for Smaller Data: Training GANs on small data without overfitting

Trained on a small dataset, generative adversarial networks (GANs) tend to generate either replicas of the training data or noisy output. A new method spurs them to produce satisfying variations.
Makeup applied on female faces with the help of augmented reality

A Good Look for AI: How L’Oreal uses AI to power its virtual makeup try-on

Trying on new makeup is a hassle — apply, inspect, wash off, repeat. Not to mention the tribulation of visiting brick-and-mortar stores during the pandemic. Augmented reality is helping people try on all the makeup they want without leaving home.
Data and examples related to a new technique to detect portions of an image

The Telltale Artifact: A technique for detecting GAN-generated deepfakes

Deepfakes have gone mainstream, allowing celebrities to star in commercials without setting foot in a film studio. A new method helps determine whether such endorsements — and other images produced by generative adversarial networks — are authentic.
Realistic portraits of historical figures Vincent van Gogh, Napoleon Bonaparte and Queen Elizabeth

Photos From Before Photos Existed: How Artbreeder generates AI images of historical figures

An artist is using deep learning to create realistic portraits of historical figures like Napoleon Bonaparte, Vincent Van Gogh, and England’s first Queen Elizabeth.
Examples of high-resolution versions of low-resolution images.

Image Resolution in Black and White: Behind the Pulse controversy about bias in machine learning

A new model designed to sharpen images tends to turn some dark faces white, igniting fresh furor over bias in machine learning. Photo Upsampling via Latent Space Exploration (Pulse) generates high-resolution versions of low-resolution images.
Illustration of three identical reindeers

Deepfakes Go Mainstream: Why 2019 was a big year for deepfakes

Society awakened to the delight, threat, and sheer weirdness of realistic images and other media dreamed up by computers.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox