Interactive Neural Style Transfer with Artists

We present interactive painting processes in which a painter and various neural style transfer algorithms interact on a real canvas. Understanding what these algorithms' outputs achieve is then paramount to describe the creative agency in our interactive experiments. We gather a set of paired p...

Full description

Saved in:
Bibliographic Details
Main Authors Kerdreux, Thomas, Thiry, Louis, Kerdreux, Erwan
Format Journal Article
LanguageEnglish
Published 14.03.2020
Subjects
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Graphics
Computer Science - Human-Computer Interaction
Computer Science - Learning
Online AccessGet full text

Cover

More Information
Summary:We present interactive painting processes in which a painter and various neural style transfer algorithms interact on a real canvas. Understanding what these algorithms' outputs achieve is then paramount to describe the creative agency in our interactive experiments. We gather a set of paired painting-pictures images and present a new evaluation methodology based on the predictivity of neural style transfer algorithms. We point some algorithms' instabilities and show that they can be used to enlarge the diversity and pleasing oddity of the images synthesized by the numerous existing neural style transfer algorithms. This diversity of images was perceived as a source of inspiration for human painters, portraying the machine as a computational catalyst.
DOI:10.48550/arxiv.2003.06659