Increase Image Resolution Using Deep Learning MathWorks
If Y high res is the luminance of the highresolution image and Y lowres is the luminance a lowresolution image that has been upscaled using bicubic interpolation, then the input to the VDSR network is Y lowres and the network learns to predict Y residual = Y highresY lowres from the training data.. After the VDSR network learns to estimate the residual image, you can reconstruct high ...