Loading...
Lukasz Lysakowski digs through a history of design automation from book printing to modern days.
The app can process video through neural networks (even streaming video).
Neural network-based app that stylizes photos to look like works of famous artists. This one makes a classic portrait (more and more like this) while Google Stadia does the same for games.
This Android launcher uses an algorithm to automatically set up colors for app cards, based on app icons.
An editor has nurtured a robot apprentice to write simple news articles about new gadgets. Whew!
A promotional image generator for e-commerce product lists. A marketer fills a simple form with a title and an image, and then the generator proposes an endless number of variations, all of which conform to design guidelines.
A script crops movie characters for posters, then applies a stylized and localized movie title, then runs automatic experiments on a subset of users. Real magic! A new version started to personalize a poster image for different users (i.e., to show a particular actor or just a mood).
Tate Modern and Microsoft collaborated on an exhibition where a machine learning algorithm selected artworks from museum's collection. Philipp Shmitt did a similar experiment with a photo album.
A review of high-tech shoe initiatives by Nike, adidas, New Balance, and Under Armour.
IBM Watson helped 20th Century Fox to create en engaging movie trailer. Looks like they're using this experiment at scale now.