Problem about "4.4 Experiments on Spatially Variant Degradation"

cszn / SRMD

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (CVPR, 2018) (Matlab)

http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Learning_a_Single_CVPR_2018_paper.pdf

422 stars 80 forks source link

Problem about "4.4 Experiments on Spatially Variant Degradation" #20

Open YuqiangY opened 3 years ago

YuqiangY commented 3 years ago

Thanks for your amazing work! But I have a question that does " synthesize an LR image with spatially variant blur kernels and noise levels" in 4.4 mean one image and multiple anisotropic Gaussian kernels and noises? And is the model trained and tested with only isotropic Gaussian kernel as input in this experiment? If you could tell me more details, I will appreciate it!