Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (19): 32-43.DOI: 10.3778/j.issn.1002-8331.2105-0296

Previous Articles     Next Articles

Review of Neural Style Transfer Models

TANG Renwei, LIU Qihe, TAN Hao   

  1. School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China
  • Online:2021-10-01 Published:2021-09-29

神经风格迁移模型综述

唐稔为,刘启和,谭浩   

  1. 电子科技大学 信息与软件学院,成都 610054

Abstract:

Neural Style Transfer(NST) technique is used to simulate different art styles of images and videos, which is a popular topic in computer vision. This paper aims to provide a comprehensive overview of the current progress towards NST. Firstly, the paper reviews the Non-Photorealistic Rendering(NPR) technique and traditional texture transfer. Then, the paper categorizes current major NST methods and gives a detailed description of these methods along with their subsequent improvements. After that, it discusses various applications of NST and presents several evaluation methods which compares different style transfer models both qualitatively and quantitatively. In the end, it summarizes the existing problems and provides some future research directions for NST.

Key words: Neural Style Transfer(NST), deep learning, convolution neural network, generative model, generative adversarial network

摘要:

神经风格迁移技术主要用于对图像、视频等进行风格化,使其具有艺术美感,该领域极具应用价值,是人工智能的热门研究领域之一。为推动神经风格迁移领域的研究发展,对神经风格迁移技术进行了全面概述。简述了非真实感渲染技术和传统的纹理迁移技术。对现有神经风格迁移模型进行了分类整理,并详细探讨了各类代表性模型的算法原理及后续改进,分析了神经风格迁移技术的应用市场。提出对风格迁移模型质量的评判应该从定性评估和定量评估两个方面来考虑,并从各个角度讨论了现阶段风格迁移技术存在的问题以及未来研究方向。最后强调应提高模型的综合能力,在保证生成质量的情况下提升生成速度以及泛化能力。

关键词: 神经风格迁移, 深度学习, 卷积神经网络, 生成模型, 生成对抗网络