Introduction

A pastiche is an artistic work that imitates the style of another one. Style transfer can be defined as finding a pastiche image **_p _**whose content is similar to that of a content image **_c _**but whose style is similar to that of a style image s.

Background

If you are familiar with optimization-based style transfer and feed-forward style transfer networks, feel free to skip this section.

The neural style transfer algorithm proposes the following definitions:

1. Content Similarity: two images are similar in content if their high-level features as extracted by a trained classifier are close in Euclidean distance
2. Style Similarity: two images are similar in style if their low-level features as extracted by a trained classifier share the same statistics.

#digital-art #deep-learning #neural-style-transfer #style-transfer #machine-learning