search

donggong1 / learn-optimizer-rgdn

Learning Deep Gradient Descent Optimization for Image Deconvolution. Dong Gong, Zhen Zhang, Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Yanning Zhang. In IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020.
https://arxiv.org/pdf/1804.03368.pdf
MIT License
32 stars 11 forks source link

The gray scale images deblurring result are not as good as paper said #7

Open TMAN1772 opened 3 years ago

TMAN1772 commented 3 years ago

Hi, I run the testing code with the testing data, the deblurred image looks well. But when I tested it on Levin's et.al dataset, the deblurred images looks bad. There are a lots of 'noise' remaining on the images. I repeat the gray scale noisy and blurred image 3 times to create the input data.

LiuzhuForFun commented 2 years ago

Hi, Can you give me some suggestions? @TMAN1772

LiuzhuForFun commented 2 years ago

I met the similar problem