GAN-Based Image Deblurring Using DCT Loss With Customized Datasets

GAN-Based Image Deblurring Using DCT Loss With Customized Datasets

In this paper, we propose a high quality image deblurring method that uses discrete cosine transform (DCT) and requires less computational complexity. We train our model on a new dataset which is customized to include images with large motion blurs. Recently, Convolutional Neural Network (CNN) and G...

Full description

Bibliographic Details
Main Authors: Hiroki Tomosada, Takahiro Kudo, Takanori Fujisawa, Masaaki Ikehara
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Image deblurring
blind deconvolution
non-uniform
GAN
discrete cosine transform (DCT)
Online Access:https://ieeexplore.ieee.org/document/9551883/

Internet

https://ieeexplore.ieee.org/document/9551883/

Similar Items