Closed QuantumLiu closed 4 years ago
Accroding to your descriptions and codes, the model need noise level and blur kernel as inputs. But we don't know these two params for an unknown images. So how can we use it for real applications?
USRNet is a non-blind SR method. You need to use other methods to estimate the blur kernel.
Accroding to your descriptions and codes, the model need noise level and blur kernel as inputs. But we don't know these two params for an unknown images. So how can we use it for real applications?