Exploring the Neural Algorithm of Artistic Style

TL;DR

This paper investigates the neural style transfer method, exploring its parameters, comparing implementations, and proposing new style representations to enhance local and content-aware style transfer capabilities.

Contribution

It extends the original neural style transfer method by analyzing hyper-parameters, comparing implementations, and introducing new style representations for improved transfer.

Findings

Varying hyper-parameters affects style transfer results.

Synthetic images can be generated by maximizing Gram matrix entries.

New style representations enable local and content-aware style transfer.

Abstract

We explore the method of style transfer presented in the article "A Neural Algorithm of Artistic Style" by Leon A. Gatys, Alexander S. Ecker and Matthias Bethge (arXiv:1508.06576). We first demonstrate the power of the suggested style space on a few examples. We then vary different hyper-parameters and program properties that were not discussed in the original paper, among which are the recognition network used, starting point of the gradient descent and different ways to partition style and content layers. We also give a brief comparison of some of the existing algorithm implementations and deep learning frameworks used. To study the style space further we attempt to generate synthetic images by maximizing a single entry in one of the Gram matrices $\mathcal{G}_l$ and some interesting results are observed. Next, we try to mimic the sparsity and intensity distribution of Gram matrices obtained from a real painting and generate more complex textures. Finally, we propose two new style representations built on top of network's features and discuss how one could be used to achieve local and potentially content-aware style transfer.