Deep plug-and-play and deep unfolding methods for image restoration

2022 ◽  
pp. 481-509
Author(s):  
Kai Zhang ◽  
Radu Timofte
Keyword(s):  
Image Restoration ◽  
Plug And Play

scholarly journals Plug-and-Play Image Restoration with Deep Denoiser Prior

2021 ◽  
pp. 1-1
Author(s):  
Kai Zhang ◽  
Yawei Li ◽  
Wangmeng Zuo ◽  
Lei Zhang ◽  
Luc Van Gool ◽  
...  
Keyword(s):  
Image Restoration ◽  
Plug And Play

Stacking Networks Dynamically for Image Restoration Based on the Plug-and-Play Framework

2020 ◽  
pp. 446-462
Author(s):  
Haixin Wang ◽  
Tianhao Zhang ◽  
Muzhi Yu ◽  
Jinan Sun ◽  
Wei Ye ◽  
...  
Keyword(s):  
Image Restoration ◽  
Plug And Play

scholarly journals Image Restoration using Plug-and-Play CNN MAP Denoisers

2020 ◽  
Author(s):  
Siavash Bigdeli ◽  
David Honzátko ◽  
Sabine Süsstrunk ◽  
L. Dunbar
Keyword(s):  
Image Restoration ◽  
Plug And Play

Primal-Dual Plug-and-Play Image Restoration

2017 ◽  
Vol 24 (8) ◽  
pp. 1108-1112 ◽  
Author(s):  
Shunsuke Ono
Keyword(s):  
Image Restoration ◽  
Plug And Play ◽  
Primal Dual

scholarly journals Plug-and-Play Prior Based on Gaussian Mixture Model Learning for Image Restoration in Sensor Network

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 78113-78122 ◽  
Author(s):  
Mingzhu Shi ◽  
Liang Feng
Keyword(s):  
Image Restoration ◽  
Sensor Network ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Gaussian Mixture ◽  
Model Learning ◽  
Plug And Play

Image Restoration and Reconstruction using Targeted Plug-and-Play Priors

2019 ◽  
Vol 5 (4) ◽  
pp. 675-686 ◽  
Author(s):  
Afonso M. Teodoro ◽  
Jose M. Bioucas-Dias ◽  
Mario A. T. Figueiredo
Keyword(s):  
Image Restoration ◽  
Plug And Play

Hyperspectral Image Restoration by Tensor Fibered Rank Constrained Optimization and Plug-and-Play Regularization

2021 ◽  
pp. 1-17
Author(s):  
Yun-Yang Liu ◽  
Xi-Le Zhao ◽  
Yu-Bang Zheng ◽  
Tian-Hui Ma ◽  
Hongyan Zhang
Keyword(s):  
Constrained Optimization ◽  
Image Restoration ◽  
Hyperspectral Image ◽  
Plug And Play

scholarly journals Plug-and-Play ADMM for Image Restoration: Fixed-Point Convergence and Applications

2017 ◽  
Vol 3 (1) ◽  
pp. 84-98 ◽  
Author(s):  
Stanley H. Chan ◽  
Xiran Wang ◽  
Omar A. Elgendy
Keyword(s):  
Fixed Point ◽  
Image Restoration ◽  
Plug And Play

Analysis of 3-d molecular distribution with the digital imaging microscope

1988 ◽  
Vol 46 ◽  
pp. 40-41
Author(s):  
W.A. Carrington ◽  
F.S. Fay ◽  
K.E. Fogarty ◽  
L. Lifshitz
Keyword(s):  
Image Restoration ◽  
Digital Imaging ◽  
Fluorescent Dyes ◽  
Optical Axis ◽  
Computer Hardware ◽  
Computer Algorithms ◽  
Low Contrast ◽  
Specific Proteins ◽  
Effective Use ◽  
Single Living Cells

Advances in digital imaging microscopy and in the synthesis of fluorescent dyes allow the determination of 3D distribution of specific proteins, ions, GNA or DNA in single living cells. Effective use of this technology requires a combination of optical and computer hardware and software for image restoration, feature extraction and computer graphics.The digital imaging microscope consists of a conventional epifluorescence microscope with computer controlled focus, excitation and emission wavelength and duration of excitation. Images are recorded with a cooled (-80°C) CCD. 3D images are obtained as a series of optical sections at .25 - .5 μm intervals.A conventional microscope has substantial blurring along its optical axis. Out of focus contributions to a single optical section cause low contrast and flare; details are poorly resolved along the optical axis. We have developed new computer algorithms for reversing these distortions. These image restoration techniques and scanning confocal microscopes yield significantly better images; the results from the two are comparable.

Sign in / Sign up

Export Citation Format

Share Document