ATFaceGAN: Single Face Semantic Aware Image Restoration and Recognition from Atmospheric Turbulence

被引：29

作者：

Lau C.P. ^{[1
]}

Castillo C.D. ^{[1
]}

Chellappa R. ^{[1
]}

机构：

[1] AIEM Laboratory, Johns Hopkins University, Baltimore, MD

来源：

IEEE Transactions on Biometrics, Behavior, and Identity Science | 2021年 / 3卷 / 02期

关键词：

face recognition; face verification; generative adversarial networks; Image restoration; turbulence mitigation;

D O I：

10.1109/TBIOM.2021.3058316

中图分类号：

学科分类号：

摘要：

Degradation due to atmospheric turbulence is common while capturing images at long ranges. To mitigate the degradation due to turbulence which includes deformation and blur, we propose a generative single frame restoration algorithm which disentangles the blur and deformation due to turbulence and reconstructs a restored image. The disentanglement is achieved by decomposing the distortion due to turbulence into blur and deformation components using a deblur generator and a deformation correction generator, respectively. Two paths of restoration are implemented to regularize the disentanglement and generate two restored images from a given degraded image. A fusion function combines the features of the restored images to reconstruct a sharp image with rich details. Adversarial and perceptual losses are added to reconstruct a sharp image and suppress the artifacts respectively. Extensive experiments demonstrate the effectiveness of the proposed restoration algorithm, which achieves satisfactory performance for face restoration and face recognition tasks. © 2019 IEEE.

引用

页码：240 / 251

页数：11

共 54 条

[1]

Hufnagel R., Stanley N., Modulation transfer function associated with image transmission through turbulent media, J. Opt. Soc. America A, 54, 1, pp. 52-61, (1964)

[2]

Roggemann M.C., Welsh B.M., Hunt B.R., Imaging through Turbulence, (1996)

[3]

Oreifej O., Li X., Shah M., Simultaneous video stabilization and moving object detection in turbulence, IEEE Trans. Pattern Anal. Mach. Intell., 35, 2, pp. 450-462, (2013)

[4]

Chen E., Haik O., Yitzhaky Y., Detecting and tracking moving objects in long-distance imaging through turbulent medium, Appl. Opt., 53, 6, pp. 1181-1190, (2014)

[5]

Pearson J.E., Atmospheric turbulence compensation using coherent optical adaptive techniques, Appl. Opt., 15, 3, pp. 622-631, (1976)

[6]

Tyson R.K., Principles of Adaptive Optics, (2015)

[7]

Furhad M.H., Tahtali M., Lambert A., Restoring atmosphericturbulence-degraded images, Appl. Opt., 55, 19, pp. 5082-5090, (2016)

[8]

Hirsch M., Sra S., Scholkopf B., Harmeling S., Efficient filter flow for space-variant multiframe blind deconvolution, Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 607-614, (2010)

[9]

Zhu X., Milanfar P., Removing atmospheric turbulence via spaceinvariant deconvolution, IEEE Trans. Pattern Anal. Mach. Intell., 35, 1, pp. 157-170, (2013)

[10]

Micheli M., Lou Y., Soatto S., Bertozzi A.L., A linear systems approach to imaging through turbulence, J. Math. Imag. Vis., 48, 1, pp. 185-201, (2014)

← 1 2 3 4 5 6 →