Reviews: Unsupervised Learning of Artistic Styles with Archetypal Style Analysis

The paper presents a novel approach to alter the artistic style of images. This is achieved by combining an unsupervised style transfer method [11] with archetypal analysis [3] to learn style representations of collections of paintings (style images). Archetypes are computed for GanGogh and Vincent van Gogh paintings to learn style characteristics, which allows different stylization effects by changing the latent space of the archetypical representation. Due to the archetypical style representation, style changes remain interpretable. The style transfer is done in a hierarchical fashion similar to [11] by matching the first and second order statistics of the content and style feature maps (introduced as whitening and coloring transformations in [11]).