Ridi, Pagliaccio !

Neural style transfer for videos.

Ridi, Pagliaccio !

Neural style transfer for videos.

Some time ago, I wrote a post on neural style transfer. Among other things, I argued that it was the perfect domain where people from the “hard sciences” and people from the humanities and social sciences could work together.

Today I’d like to exemplify this further by showing how I applied this technique to a pre-existing video .

The original video shows the Ohbot, a robot head I programmed in Python, lip-syncing to a famous tenor opera aria:

The transformed video contains 15 different styles. Apart from the very beginning and end of the video, the video frames were submitted to style transfer (each style lasts about 3 sec.). Here’s the list in random order:

  1. The Mona Lisa by Leonardo da Vinci
  2. Composition VI by Vassily Kandinsky
  3. The Weeping Woman by Pablo Picasso
  4. Portrait of Adele Bloch-Bauer I by Gustav Klimt
  5. Port en Normandie by Georges Braque
  6. La Couleur Tombée du Ciel by Marc Chagall
  7. Several Circles by Vassily Kandinsky
  8. (unknown title) by Victor Figol
  9. Tableau I by Piet Mondrian
  10. The Fox by Franz Marc
  11. La récolte des pommes à Éragny by Camille Pissarro
  12. Le Repas de Gargantua by Gustave Doré
  13. The Scream by Edvard Munch
  14. The Women of Algiers Version O by Pablo Picasso
  15. The Starry Night by Vincent van Gogh

ENJOY !!!

Avatar
Emmanuel Ferragne
Associate Professor of Phonetics

Phonetician, AI enthusiast, occasional musician, amateur kickboxer.

Related