Artwork by Gene Kogan presents observers in the style of a Cubist composition, using the neural network Style Transfer method:
A near-real-time style transfer mirror based on ‘Perceptual losses for
real-time style transfer’ from Johnson et al, trained on an unidentified
Cubist painting.
The work is part of an exhibition alt-AI exploring how Artificial Intelligence can be used in artistic practice - you can find out more here
Reblogging to include latest video documentation:
Cubist Mirror is a mirror which reflects the world back in the Cubist painting style.
It was first installed for alt-AI, a conference about art &
artificial intelligence which occurred in May 2016 at The School for
Poetic Computation in New York. The mirror is an LCD screen with a
webcam to the side, running an openFrameworks application which
continuously applies a real-time variant of the style transfer technique
to the camera feed.
