StyleGAN

10 Posts

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

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
3 min read
Detection of a digitally altered image of a frog holding a violin
StyleGAN

Fighting Fakes

A supergroup of machine learning models flags manipulated photos. Jigsaw, a tech incubator owned by Alphabet, released a system that detects digitally altered images.
1 min read
Examples of image generators using GANsformer
StyleGAN

Attention for Image Generation

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.
2 min read
Tree farm dataset
StyleGAN

Representing the Underrepresented

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.
2 min read
Examples of AI generated images
StyleGAN

GANs for Smaller Data

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.
2 min read
Makeup applied on female faces with the help of augmented reality
StyleGAN

A Good Look for AI

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.
2 min read
Data and examples related to a new technique to detect portions of an image
StyleGAN

The Telltale Artifact

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.
2 min read
Realistic portraits of historical figures Vincent van Gogh, Napoleon Bonaparte and Queen Elizabeth
StyleGAN

Photos From Before Photos Existed

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.
1 min read
Examples of high-resolution versions of low-resolution images.
StyleGAN

Image Resolution in Black and White

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.
2 min read
Illustration of three identical reindeers
StyleGAN

Deepfakes Go Mainstream

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

Subscribe to The Batch

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