Exploring the Neural Algorithm of Artistic Style

By Yaroslav Nikulin, Roman Novak. 2016

40 citations recorded by the source corpus.

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.

Subfields: Cognitive Neuroscience, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

1. Mingli Song
2. Kun He
3. John E. Hopcroft
4. Thomas Brox
5. Alexey Dosovitskiy
6. Manuel Ruder
7. Jingwen Ye
8. Yan Wang

In Computer Graphics and Computer-Aided Design

1. Alexey Dosovitskiy
2. Thomas Brox
3. Mingli Song
4. Kun He
5. John E. Hopcroft
6. Manuel Ruder
7. Jingwen Ye
8. Yan Wang

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Yezhou Yang
3. Luc Van Gool
4. Yi Yang
5. Xiaogang Wang
6. Mingli Song
7. Bernt Schiele
8. Jitendra Malik

Citations in the corpus

• Neural Style Transfer: A Review (2017, background): “Novak and Nikulin [34] address the issue that style representation in [14] is invariant to the spatial configuration of the style image and propose a new style representation called “spatial style”, which captures less style details and more spatial configurations.”
• A Powerful Generative Model Using Random Weights for the Deep Image Representation (2016, methodology): “[13] then combine the loss on the correlations as a proxy to the style of a painting and the loss on the activations to represent the content of an image, and successfully create artistic images by converting the artistic style to the content image, inspiring several followups [14, 15].”
• Artistic Style Transfer for Videos and Spherical Images (2017, methodology): “[19] tried the style transfer algorithm on features from”