Neural Style Transfer: A Review

Abstract

The seminal work of Gatys et al. demonstrated the power of Convolutional Neural Networks (CNNs) in creating artistic imagery by separating and recombining image content and style. This process of using CNNs to render a content image in different styles is referred to as Neural Style Transfer (NST). Since then, NST has become a trending topic both in academic literature and industrial applications. It is receiving increasing attention and a variety of approaches are proposed to either improve or extend the original NST algorithm. In this paper, we aim to provide a comprehensive overview of the current progress towards NST. We first propose a taxonomy of current algorithms in the field of NST. Then, we present several evaluation methods and compare different NST algorithms both qualitatively and quantitatively. The review concludes with a discussion of various applications of NST and open problems for future research. A list of papers discussed in this review, corresponding codes, pre-trained models and more comparison results are publicly available at https://github.com/ycjing/Neural-Style-Transfer-Papers.

Project page: https://github.com/ycjing/Neural-Style-Transfer-Papers

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Learned Representation For Artistic Style
• Disentangling by Factorising
• Multimodal Unsupervised Image-to-Image Translation
• Fast Patch-based Style Transfer of Arbitrary Style
• Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations
• Multi-style Generative Network for Real-time Transfer
• A Closed-form Solution to Photorealistic Image Stylization
• Neural Style Transfer for Audio Spectograms
• ZM-Net: Real-time Zero-shot Image Manipulation Network
• Time Domain Neural Audio Style Transfer

Cited by in corpus (25)

• Generating Handwritten Chinese Characters using CycleGAN
• Multi-style Generative Network for Real-time Transfer
• Audio style transfer
• Neural Painters: A learned differentiable constraint for generating brushstroke paintings
• Applying Visual Domain Style Transfer and Texture Synthesis Techniques to Audio - Insights and Challenges
• Attention-aware Multi-stroke Style Transfer
• High-Resolution Network for Photorealistic Style Transfer
• A Closed-form Solution to Universal Style Transfer
• Generate Identity-Preserving Faces by Generative Adversarial Networks
• Recent Advances of Image Steganography with Generative Adversarial Networks
• AffinityNet: semi-supervised few-shot learning for disease type prediction
• Mask Based Unsupervised Content Transfer
• Style transfer-based image synthesis as an efficient regularization technique in deep learning
• EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer
• Im2Pencil: Controllable Pencil Illustration from Photographs
• WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image Classification
• Sketch-to-Art: Synthesizing Stylized Art Images From Sketches
• Semantic Attribute Matching Networks
• Learning Selfie-Friendly Abstraction from Artistic Style Images
• Computationally Efficient Approaches for Image Style Transfer
• GANILLA: Generative Adversarial Networks for Image to Illustration Translation
• A Neural Embeddings Approach for Detecting Mobile Counterfeit Apps
• Dialectical GAN for SAR Image Translation: From Sentinel-1 to TerraSAR-X
• Neural Comic Style Transfer: Case Study
• Learning to Transfer Visual Effects from Videos to Images