Combining Spatial and Frequency Information for Image Deblurring

This letter aims to combine spatial and frequency information for single image deblurring. Although some methods have tried to use frequency information to perform deblurring, they only simply process the different frequencies information separately or concatenate the real part and imaginary part of...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2022, Vol.29, p.1679-1683
Main Authors: Hai, Jiang, Yang, Ren, Yu, Yaqi, Han, Songchen
Format: Article
Language:English
Subjects:
Conversion
Correlation
Fast Fourier transform
Frequency conversion
Frequency-domain analysis
image deblurring
Image restoration
Kernel
multi-scale network
Pipelines
spatial and frequency conversion
Spatial data
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This letter aims to combine spatial and frequency information for single image deblurring. Although some methods have tried to use frequency information to perform deblurring, they only simply process the different frequencies information separately or concatenate the real part and imaginary part of frequency features but ignore the strong correlation between them. To address this problem, we propose a simple but effective frequency interaction pipeline to realize the mutual conversion of the real part and the imaginary part. Then, we construct a spatial-frequency conversion module (SFCM) to promote the mutual conversion between the frequency information and the spatial information. Based on the proposed components, we build a multi-scale deblurring network, dubbed SFDNet, which can fully exploit coarse and middle-level information in spatial and frequency domains for finer scale image deblurring. Extensive experiments on the GoPro and HIDE datasets demonstrate that the proposed network outperforms the state-of-the-art methods both quantitatively and visually.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2022.3194807