Image Style Transfering Based on StarGAN and Class Encoder

被引：0
|
作者：
Xu X.-Z. [1 ,2 ]
Chang J.-Y. [1 ]
Ding S.-F. [1 ,2 ]
机构：
[1] School of Computer Science and Technology, China University of Mining and Technology, Xuzhou
[2] Engineering Research Center of Mining Digitalization of Ministry of Education (China University of Mining and Technology), Xuzhou
来源：
Ruan Jian Xue Bao/Journal of Software | 2022年 / 33卷 / 04期
关键词：
Class encoder; Generative adversarial network; Image style transfering; StarGAN; U-Net;
D O I：
10.13328/j.cnki.jos.006482
中图分类号：
学科分类号：
摘要：
The image style transferring technology has been widely integrated into people's life, and it is widely used in image artistry, cartoon, picture coloring, filter processing, and occlusion removal of the practical scenarios, so image style transfering has an important research significance and application value. StarGAN is a generative adversarial network framework for multi-domain image style transfering in recent years. StarGAN extracts features through simple down-sampling, and then generates images through up-sampling. Nevertheless, the background color information and detailed features of people's faces in the generated images are quite different from those in the input images. In this study, by improving the network structure of StarGAN, after analyzing the existing problems of the StarGAN, a UE-StarGAN model for image style transfering is proposed by introducing U-Net and edge-promoting adversarial loss function. At the same time, the class encoder is introduced into the generator of UE-StarGAN, and a small sample image style transfering model is designed to realize the small sample image style transfer. The results of this experiment show that the model can extract more detailed features, have some advantages in the case of small sample size, and to a certain extent, the qualitative and quantitative analysis results of the images can be improved after the image style transfering, which verifies the effectiveness of the proposed model. © Copyright 2022, Institute of Software, the Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：1516 / 1526
页数：10
相关论文
共 27 条
  • [1] Ligeza A., Artificial intelligence: A modern approach, Applied Mechanics & Materials, 263, 2, pp. 2829-2833, (2009)
  • [2] Pollack ME., Artificial intelligence-A modern approach (a review), AI Magazine, 16, pp. 73-74, (1995)
  • [3] Zhou FY, Jin LP, Dong J., Review of convolutional neural network, Chinese Journal of Computers, 40, 6, pp. 1229-1251, (2017)
  • [4] Lu HT, Zhang QC., Applications of deep convolutional neural network in computer vision, Journal of Data Acquisition and Processing, 31, 1, pp. 1-17, (2016)
  • [5] Li S., Research and development of natural language processing, Journal of Yanshan University, 37, 5, pp. 377-384, (2013)
  • [6] Goodfellow I, Pouget-Abadie J, Mirza M, Et al., Generative adversarial nets, Proc. of the Advances in Neural Information Processing Systems, pp. 2672-2680, (2014)
  • [7] Zhang D, Shao J, Hu G, Et al., Sharp and real image super-resolution using generative adversarial network, Proc. of the Int'l Conf. on Neural Information Processing, pp. 217-226, (2017)
  • [8] Ouyang N, Liang T, Lin LP., Self-attention network based image super-resolution, Journal of Computer Applications, 39, 8, pp. 2391-2395, (2019)
  • [9] Gao Y, Liu Z, Qin PL, Et al., Medical image super-resolution algorithm based on deep residual generative adversarial network, Journal of Computer Applications, 38, 9, pp. 2689-2695, (2018)
  • [10] Reed S, Akata Z, Yan X, Et al., Generative adversarial text to image synthesis, JMLR.org, (2016)
123