Archetypal Style Analysis


Authors: Daan Wynen
Cordelia Schmid
Julien Mairal

On these pages we present supplementary material for two works:

Unsupervised Learning of Artistic Styles with Archetypal Style Analysis

Published at NeurIPS 2018


We show comparisons of the \(\delta, \gamma\) style control to the control used by Li et. al. and results of our method as applied to the GanGogh collection, the collection of works by Vincent van Gogh, Claude Monet, Pierre-Auguste Renoir, as well as Wassily Kandinsky.

Learning Latent Representations of Style with Archetypal Style Analysis

Submitted to TPAMI


We show more examples of archetypal style analysis, applied to the slightly bigger WikiArt collection, as well as different subsets thereof. Namely, we analyze the works of Vincent van Gogh, Salvador Dalí, Pablo Picasso, four famous painters, and the Venetian school. We also use the WikiArt metadata to take a look at the connections between the archetypes (which are learned in a completely unsupervised way) and different concepts relevant to art history.


Using deep archetypal style analysis, we can represent an artistic image (a) as a convex combination of archetypes. The archetypes can be visualized as synthesized textures (b), as a convex combination of artworks (c) or, when analyzing a specific image, as stylized versions of that image itself (d). Free recombination of the archetypal styles (e) then allows for novel stylizations of the input.



This work was supported by a grant from ANR (MACARON project under grant number ANR-14-CE23-0003-01), by the ERC grant number 714381 (SOLARIS project) and the ERC advanced grant Allegro.