jiangsutx / SRN-Deblur

Repository for Scale-recurrent Network for Deep Image Deblurring
http://www.xtao.website/projects/srndeblur/srndeblur_cvpr18.pdf
MIT License
714 stars 184 forks source link

Excuse me, I want to know why you choose ConvLSTM between Encoder and Decoder? #19

Closed strawberry1996 closed 3 years ago

jiangsutx commented 5 years ago

In the paper, we explained that we want propagate information across different scales. And convLSTM is a common module for recurrent networks.