CEILNet
CEILNet copied to clipboard
fqnchina
Implementation of ICCV 2017 paper "A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing"
Hi, I have some questions about the selection of dataset in your work. You put the index of training data into the txt file. However, could you tell me according...
Hi, How do I save the synthetic training dataset for reflection removal generated using PASCAL VOC2012 images locally? Is it being generated on the fly? Could you please provide code...
excuse me, i wonder how to use this code train on myself data? i'm a beginner to lua torch. is there any other version like keras, tensorflow? thanks.
Hi, I trained the ecnn individually using the provided codes (training_reflection_ecnn.lua) but found that the loss went down from about 10^8 to about 10^6 and just stuck. Tracing the code,...
In line 230 of training_reflection_ecnn.lua, optim.adam_state was a nil value as I called it. You mean optim.adam?
Hi, As you have mentioned in your paper 4-1, the sub-networks are trained separately. I just wonder about how you obtain the label of your E-CNN, which should be an...
This is very interesting work, thanks for sharing! Is it possible to also post the ground truth (e.g. transmission and reflection layer) of the synthetic dataset? Thanks for the consideration!
