images without labels about dasr HOT 1 OPEN

Hi @happy20200, thanks for your ineterest in our work.
In our network, the learning of degradation representation is unsupervised while the learning of SR still requires the supervision from LR-HR image pairs. To conduct training on real images (without paired images), I think you can try the loss function for unpaired SR like in [a].

[a] To learn image super-resolution, use a GAN to learn how to do image degradation first, ECCV 2018

from dasr.