# Neural Style Transfer: A Review

**Authors:** Yongcheng Jing, Yezhou Yang, Zunlei Feng, Jingwen Ye, Mingli Song  
**arXiv:** [1705.04058](https://arxiv.org/abs/1705.04058)  
**Date:** 2017-05-11  
**Summary page:** https://www.summarizepaper.com/en/paper/1705.04058v1/

## Key points

- Authors discuss recent advancements in Neural Style Transfer (NST)
- Highlight the groundbreaking work of Gatys et al. in using CNN for generating artistic imagery
- NST has gained significant attention from academia and industry
- Several methods proposed to improve or extend the original neural algorithm
- No comprehensive survey currently available on NST literature
- Review aims to provide an overview of current progress in NST
- Discussion of various applications of NST and identification of open problems for future research
- Review helps readers gain a deeper understanding of NST and its implications across different fields
- Valuable guidance for researchers looking to contribute to this field

## Summary

In their paper titled "Neural Style Transfer: A Review," authors Yongcheng Jing, Yezhou Yang, Zunlei Feng, Jingwen Ye, and Mingli Song discuss the recent advancements in Neural Style Transfer (NST). They begin by highlighting the groundbreaking work of Gatys et al., which showcased the power of Convolutional Neural Networks (CNN) in generating artistic imagery by separating and recombining image content and style. This process involves using CNN to transfer the semantic content of one image onto different styles. Since its introduction, NST has gained significant attention from both academia and industry. It has become a trending topic in computer vision research due to its potential applications in various domains. Researchers have proposed several methods to improve or extend the original neural algorithm presented by Gatys et al. Despite the growing interest in NST, there is currently no comprehensive survey that summarizes recent literature on this topic. Therefore, this review aims to fill that gap by providing an overview of the current progress made towards NST. The authors also discuss various applications of NST and highlight open problems for future research. By delving into this review, readers can gain a deeper understanding of NST and its potential implications across different fields. The authors' analysis of existing techniques and identification of research gaps will serve as valuable guidance for researchers looking to contribute to this rapidly evolving field. Overall, this comprehensive review contributes to advancing the knowledge and understanding of Neural Style Transfer.