Premium
Image Deblurring of Camera Under Display by Deep Learning
Author(s) -
Zhang Zhenhua
Publication year - 2020
Publication title -
sid symposium digest of technical papers
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.351
H-Index - 44
eISSN - 2168-0159
pISSN - 0097-966X
DOI - 10.1002/sdtp.13747
Subject(s) - deblurring , artificial intelligence , computer vision , computer science , pixel , oled , computer graphics (images) , deep learning , image (mathematics) , image processing , image restoration , materials science , layer (electronics) , composite material
A deep learning method is provided in this paper to deblur images captured behind OLED screen named Camera Under Display (CUD). Because of optical diffraction of OLED pixel pattern, images captured by front camera under the display panel are unfavorably blurred. This paper proposed a modified GAN training network to deblur these images, with result showing perceptually clearer image with better restored high spatial frequency information.