Face hallucination based on edge enhanced generative adversarial network

被引：0

作者：

Lu T. ^{[1
,2
]}

Chen C. ^{[1
]}

Xu R. ^{[1
]}

Zhang Y. ^{[1
,2
]}

机构：

[1] School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan

[2] Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan

来源：

Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2020年 / 48卷 / 01期

关键词：

Edge enhanced network; Edge fusion; Face hallucination; Generative adversarial network; Parallel network;

D O I：

10.13245/j.hust.200116

中图分类号：

学科分类号：

摘要：

Aiming at the imperfection of the countermeasure generation neural network in the restoration of facial contour details, an edge enhancement generation countermeasure network was proposed to enhance the super-resolution reconstruction performance of human face based on the prior structural information of face images.First, a parallel network was designed by using the consistency relationship between face images and their edge images.The network extracted facial and edge detail features, and then high-resolution generated images were obtained by feature fusion network.Finally, the authenticity of generated images was distinguished by discriminant network.Experimental results of face super-resolution reconstruction on face image database by the proposed algorithm show that the proposed edge enhancement generates confrontation network can improve the ability of facial detail reconstruction, and the subjective and objective evaluation indexes are superior to the existing frontier face super-resolution algorithms. © 2020, Editorial Board of Journal of Huazhong University of Science and Technology. All right reserved.

引用

页码：87 / 92

页数：5

共 12 条

[1]

Nasrollahi K., Moeslund T.B., Super-resolution: a comprehensive survey, Machine Vision and Applica- Tions, 25, 6, pp. 1423-1468, (2014)

[2]

Dong C., Loy C.C., He K.M., Et al., Image superresolution using deep convolutional networks, IEEE Transactions on Pattern Analysis and Machine Intel-Ligence, 38, 2, pp. 295-307, (2015)

[3]

Kim J., Kwon L., Mu L., Accurate image superresolution using very deep convolutional networks, Proc of Computer Vision and Pattern Recognition, pp. 1646-1654, (2016)

[4]

Ledig C., Theis L., Huszar F., Et al., Photo-realistic single image super-resolution using a generative adversarial network, Proc of Computer Vision and Pattern Recognition, pp. 105-114, (2017)

[5]

Yang X., Lu T., Wu Y.T., Et al., Enhanced discriminative generative adversarial network for face super-resolution, Proc of Paciﬁc Rim Conference on Multimedia, pp. 441-452, (2018)

[6]

Yang W., Feng J., Yang J., Et al., Deep edge guided recurrent residual learning for image super resolution, IEEE Transactions on Image Processing, 26, 12, pp. 5895-5907, (2017)

[7]

Zhang Y., Tian Y., Kong Y., Et al., Residual dense network for image super-resolution, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2472-2481, (2018)

[8]

Huang G., Liu Z., Van D.M., Et al., Densely connected convolutional networks, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700-4708, (2017)

[9]

Johnson J., Alahi A., Li F.F., Perceptual losses for real-time style transfer and super-resolution, Proc of European Conference on Computer Vision, pp. 694-711, (2016)

[10]

Wang X., Laplacian operator-based edge detectors, IEEE Transactions on Pattern Analysis and Machine Intelligence, 29, 5, pp. 886-890, (2007)

← 1 2 →