Timezone: »

 
Poster
Unsupervised Learning of Artistic Styles with Archetypal Style Analysis
Daan Wynen · Cordelia Schmid · Julien Mairal

Tue Dec 04 02:00 PM -- 04:00 PM (PST) @ Room 210 #98
in Tue Poster Session B »

In this paper, we introduce an unsupervised learning approach to automatically dis- cover, summarize, and manipulate artistic styles from large collections of paintings. Our method is based on archetypal analysis, which is an unsupervised learning technique akin to sparse coding with a geometric interpretation. When applied to deep image representations from a data collection, it learns a dictionary of archetypal styles, which can be easily visualized. After training the model, the style of a new image, which is characterized by local statistics of deep visual features, is approximated by a sparse convex combination of archetypes. This allows us to interpret which archetypal styles are present in the input image, and in which proportion. Finally, our approach allows us to manipulate the coefficients of the latent archetypal decomposition, and achieve various special effects such as style enhancement, transfer, and interpolation between multiple archetypes.

Keywords: Computer Vision · Applications · Computational Photography

Author Information

Daan Wynen (INRIA)
Cordelia Schmid (Inria / Google)
Julien Mairal (Inria)

More from the Same Authors