search

The-Learning-And-Vision-Atelier-LAVA / DASR

[CVPR 2021] Unsupervised Degradation Representation Learning for Blind Super-Resolution
MIT License
388 stars 50 forks source link

images without labels #4

Open happy20200 opened 3 years ago

happy20200 commented 3 years ago

Hello, thank you very much for your excellent work, but I would like to know how to train the model for realistic scene images without labels

LongguangWang commented 3 years ago

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