Blur identification by multilayer neural network based on multivalued neurons
A multilayer neural network based on multivalued neurons (MLMVN) is a neural network
with a traditional feedforward architecture. At the same time, this network has a number of …
with a traditional feedforward architecture. At the same time, this network has a number of …
Joint blur kernel estimation and CNN for blind image restoration
L Huang, Y **a - Neurocomputing, 2020 - Elsevier
Convolutional neural networks (CNN) have shown its excellent performance in computer
vision fields. Recently, they are successfully applied to image restoration. This paper …
vision fields. Recently, they are successfully applied to image restoration. This paper …
Fast blind image super resolution using matrix-variable optimization
L Huang, Y **a - IEEE Transactions on Circuits and Systems …, 2020 - ieeexplore.ieee.org
Super resolution image reconstruction under unknown Gaussian blur has been a
challenging topic. Advanced optimization-based works for blind image super-resolution (SR) …
challenging topic. Advanced optimization-based works for blind image super-resolution (SR) …
Blind image blur identification in cepstrum domain
The type and extent of blur affect image quality and therefore its evaluation. This paper
presents an accurate method for blur identification and parameter estimation from one …
presents an accurate method for blur identification and parameter estimation from one …
Effective video deblurring based on feature-enhanced deep learning network for daytime and nighttime images
DY Huang, CH Chen, TY Chen, JE Li, HL Hsiao… - Multimedia Tools and …, 2024 - Springer
Motion-blurred images are usually generated when captured with a handheld or wearable
video camera, owing to rapid movement of the camera or foreground (ie, moving object …
video camera, owing to rapid movement of the camera or foreground (ie, moving object …
Blind blur assessment for vision-based applications
In this paper, a criterion for objective defocus blur measurement is theoretically derived from
one image. The essential idea is to estimate the point spread function (PSF) from the line …
one image. The essential idea is to estimate the point spread function (PSF) from the line …
A blind restoration method for remote sensing images
This letter proposes a blind image restoration method for the deblurring of remote sensing
images. A simple but robust identification method of point spread function (PSF) support is …
images. A simple but robust identification method of point spread function (PSF) support is …
Towards digital refocusing from a single photograph
This paper explores an image processing method for synthesizing refocused images from a
single input photograph containing some defocus blur. First, we restore a sharp image by …
single input photograph containing some defocus blur. First, we restore a sharp image by …
An adaptive non-local total variation blind deconvolution employing split Bregman iteration
Z Zuo, T Zhang, X Lan, L Yan - Circuits, Systems, and Signal Processing, 2013 - Springer
Total variation (TV) has been used as a popular and effective image prior model in
regularization-based image restoration, because of its ability to preserve edges. However …
regularization-based image restoration, because of its ability to preserve edges. However …