GitHub - zhjwustc/cvpr17_iter_deblur_testing_matconvnet: Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution[testing][matconvnet]

zhjwustc / cvpr17_iter_deblur_testing_matconvnet Public

Notifications You must be signed in to change notification settings
Fork 2
Star 10

Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution[testing][matconvnet]

MIT, Unknown licenses found

Licenses found

10 stars 2 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
data		data
matconvnet		matconvnet
models		models
utils		utils
COPYING		COPYING
DL_deblur.m		DL_deblur.m
LICENSE		LICENSE
bilinear_u.m		bilinear_u.m
demo.m		demo.m
findcrop.m		findcrop.m
loadNetwork.m		loadNetwork.m
psnr_ssim_img.m		psnr_ssim_img.m
readme.txt		readme.txt
ssim_index.m		ssim_index.m
wrap_boundary_liu.m		wrap_boundary_liu.m
wrap_boundary_with_edgetaper.m		wrap_boundary_with_edgetaper.m

Repository files navigation

This package contains the testing code of the image deblurring algorithm described in the paper: 
Jiawei Zhang, Jinshan Pan, Wei-Sheng Lai, Rynson W.H. Lau, Ming-Hsuan Yang, "Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution", CVPR 2017. 
----------------
How to use
----------------
1. Please install matconvnet first
(1) run matconvnet/matlab/vl_setupnn
(2) vl_compilenn('enableGpu', true)
2. run the testing code from demo.m and you can choose 1%, 3% and 5% noise.