Image recognition, reconstruction – and how AI can go wrong

Showing 4 of 8

Style transfer

Source: Johnson, Justin, Alexandre Alahi, and Li Fei-Fei. "Perceptual losses for real-time style transfer and super-resolution." European Conference on Computer Vision. Springer, Cham, 2016.

There are also more complicated forms of translation. For example, GANs can be used for something called style transfer. Here, the network "learns" a style from a painting, and then applies it to another picture. This means that you can have your favourite photo rendered in the style of a famous artist. The pictures above use paintings by Picasso and Van Gogh, but really the sky is the limit provided you have a picture to use to train the network.


About Author

Veronique Van Vlasselaer

Data science enthusiast with an infinite passion to operationalize business decisions supported by insights from data analysis, machine learning and AI; anti-fraud expert; team player who loves to work with inspiring people, main focus = having fun on the job

Leave A Reply

Back to Top