search

yulunzhang / RDN

Torch code for our CVPR 2018 paper "Residual Dense Network for Image Super-Resolution" (Spotlight)
543 stars 108 forks source link

Regarding intuition compareed to MemNet #24

Open jaytimbadia opened 2 years ago

jaytimbadia commented 2 years ago

Hi, Really loved reading the paper!

I just had one small confusion. What is MemNet lacking that you are trying to resolve?

Your point from the paper: MemNet interpolates the original LR image to the desired size to form the input. This preprocessing step not only increases computation complexity quadratically but also loses some details of the original LR image.

I have read MenNet they also do have the same feature extraction initial network as yours followed by memblocks and reconnet.

So what does this above point mean?

Thank you!

jaytimbadia commented 2 years ago

Ok. I hope I got the idea.

But still confused with one minor doubt, that do you people also do long term memory persistence just like MemNet as in adding dense connections across RDB blocks.

image

Thanks!