csdwren / SelfDeblur

Neural Blind Deconvolution Using Deep Priors (CVPR 2020)
334 stars 66 forks source link

test #13

Open yinglili666 opened 3 years ago

yinglili666 commented 3 years ago

how to do deblur on an image?

csdwren commented 3 years ago

Please refer to https://github.com/csdwren/SelfDeblur/blob/master/selfdeblur_ycbcr.py. You need to provide datapath to test blurry images and blur kernel size.

yinglili666 commented 3 years ago

Please refer to https://github.com/csdwren/SelfDeblur/blob/master/selfdeblur_ycbcr.py. You need to provide datapath to test blurry images and blur kernel size.

thank you. but my images are real blur, how should I set blur kernel size?

csdwren commented 3 years ago

In existing most deblurring methods, blur kernel size should be tuned. I suggest trying to set it as a large size.

yinglili666 commented 3 years ago

In existing most deblurring methods, blur kernel size should be tuned. I suggest trying to set it as a large size. I would also like to ask about the time cost of this algorithm. It seems that it takes several minutes to calculate a picture. Where is the problem with my operation that leads to such a long processing time

csdwren commented 3 years ago

Given an image, this method optimizes two deep generators from scratch. Thus it takes long time, which is the main disadvantage of this method.

CaptainEven commented 3 years ago

@csdwren So, this method is not applicable in industry applications right?