A super resolution is produced using multiple reference images. Reference images are upsampled and blurred as needed for comparison between images of different resolution. Patches in blurred images are searched to find those patches which can be assembled into vectors for improving feature content over multiple resolution levels. The searches are based on similarity maps. The assembled vectors are concatenated with one or more other vectors, up-converted and then passed through convolutional layers to obtain new feature vectors. A final feature vector is passed through a convolutional layer to obtain the super resolution image.