Circular LBP Prior-Based Enhanced GAN for Image Style Transfer

Wenguang Qian, Hua Li, Haiping Mu

Source Title: International Journal on Semantic Web and Information Systems (IJSWIS)18(2)

ISSN: 1552-6283|EISSN: 1552-6291|EISBN13: 9781799893974|DOI: 10.4018/IJSWIS.315601

MLA

Qian, Wenguang, et al. "Circular LBP Prior-Based Enhanced GAN for Image Style Transfer." IJSWIS vol.18, no.2 2022: pp.1-15. http://doi.org/10.4018/IJSWIS.315601

APA

Qian, W., Li, H., & Mu, H. (2022). Circular LBP Prior-Based Enhanced GAN for Image Style Transfer. International Journal on Semantic Web and Information Systems (IJSWIS), 18(2), 1-15. http://doi.org/10.4018/IJSWIS.315601

Chicago

Qian, Wenguang, Hua Li, and Haiping Mu. "Circular LBP Prior-Based Enhanced GAN for Image Style Transfer," International Journal on Semantic Web and Information Systems (IJSWIS) 18, no.2: 1-15. http://doi.org/10.4018/IJSWIS.315601

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

Image style transfer (IST) has drawn broad attention recently. At present, convolutional neural network (CNN)-based methods and generative adversarial network (GAN)-based methods have been broadly utilized in IST. However, the texture of images obtained by most methods presents a lower definition, which leads to insufficient details of IST. To this end, the authors present a new IST method based on an enhanced GAN with a prior circular local binary pattern (LBP). They utilize circular LBP in a GAN generator as a texture prior to improve the detailed textures of the generated style images. Meanwhile, they integrate a dense connection residual block and an attention mechanism into the generator to further improve high-frequency feature extraction. In addition, the total variation (TV) regularizer is integrated into the loss function to smooth the training results and restrain the noise. The qualitative and quantitative experimental results demonstrate that the metric quality of the generated images can achieve better effects by the proposed strategy compared with other popular approaches.