Exploring the Neural Algorithm of Artistic Style

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.

A short class project report (14 pages, 14 figures)

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Going Deeper with Convolutions
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks

Cited by in corpus (9)

• Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks
• Incorporating long-range consistency in CNN-based texture generation
• Applying Visual Domain Style Transfer and Texture Synthesis Techniques to Audio - Insights and Challenges
• Quantitative Evaluation of Style Transfer
• Neural Abstract Style Transfer for Chinese Traditional Painting
• Style transfer-based image synthesis as an efficient regularization technique in deep learning
• Neural Style Representations and the Large-Scale Classification of Artistic Style
• GLStyleNet: Higher Quality Style Transfer Combining Global and Local Pyramid Features
• A Comprehensive Comparison between Neural Style Transfer and Universal Style Transfer