Closed Amy-A closed 4 years ago
Hi, I am not very familiar with face super-resolution. (1) I suggest you to read some face super-resolution paper and follow their setting to train. (2) The multi scale in VDSR is they mix scale 2, 3 and 4 in training. So they can inference difference scale in only one model. (3) The most importance reason of VDSR are deep network and residual. I suggest you follow the network structure of https://arxiv.org/abs/1609.04802 to train more deeper network.
Hi Huang,thanks your sharing! But I have some question. 1.The relation of Training image data and the image I want to rebuild.I mean if i want to rebuild some low resolution images of human face. Do you think my Training data should be all the human face images? Or I should make my Training data the more types, the better?