I am not into the field of super resolution but I think this question applies to general neural network construction. Usually you try to solve a classification problem or a regression problem with your neural network. - For classification you try to predict probabilities that a specific output corrensponds to a specific class. Therefore every output value should be a probability and therefore have a range between 0 and 1. To achieve this you usually use a softmax or sigmoid function as your last layer to squash the output between 0 and 1 and give likely classes higher probabilities and unlikely classes less probability. - For the regression task you are not looking for probability values as your output values but instead for real numbers. In such a case no activation function is wanted since you want to be able to approximate any possible real value and not probabilities. So in the case of super resolution I think the generated output is a map where each value corresponds to a pixel value of the super resolution image. In that case your pixels are real number values and no probabilities. So you are solving a regression problem.