A Learned Representation For Artistic Style

TL;DR

This paper introduces a scalable deep network that captures and represents diverse artistic styles in a shared embedding space, enabling style exploration and combination.

Contribution

It presents a novel deep learning model that generalizes across multiple painting styles and allows style interpolation in a learned embedding space.

Findings

The model successfully captures a wide range of artistic styles.

It enables interpolation and combination of different styles.

The approach offers insights into the structure of artistic style representations.

Abstract

The diversity of painting styles represents a rich visual vocabulary for the construction of an image. The degree to which one may learn and parsimoniously capture this visual vocabulary measures our understanding of the higher level features of paintings, if not images in general. In this work we investigate the construction of a single, scalable deep network that can parsimoniously capture the artistic style of a diversity of paintings. We demonstrate that such a network generalizes across a diversity of artistic styles by reducing a painting to a point in an embedding space. Importantly, this model permits a user to explore new painting styles by arbitrarily combining the styles learned from individual paintings. We hope that this work provides a useful step towards building rich models of paintings and offers a window on to the structure of the learned representation of artistic style.