Computer-implemented image-processing method, image-enhancing convolutional neural network, and computer product

An image-enhancing convolutional neural network, trained by:

• obtaining a pair of a training image having a first degree of sharpness and a reference image having a second degree of sharpness, the second degree greater than the first degree, at least portions of the training image and the reference image in a same pair having same contents;
• inputting the training image to the image-enhancing convolutional neural network to generate a training enhanced image;
• inputting the training enhanced image into an edge detector;
• generating, by the edge detector, a plurality of first edge maps;
• inputting the reference image into the edge detector;
• generating, by the edge detector, a plurality of second edge maps;
• calculating one or more first losses based on the plurality of first edge maps and the plurality of second edge maps, a respective one of the one or more first losses being calculated based on a respective one of the plurality of first edge maps and a respective one of the plurality of second edge maps, the respective one of the plurality of first edge maps and the respective one of the plurality of second edge maps having a same scale;
• comparing the training enhanced image with the reference image to calculate a second loss;
• and
• tuning parameters in the image-enhancing convolutional neural network to minimize at least the one or more first losses and the second loss.

A computer-program product, for training an image-enhancing convolutional neural network configured to enhance an original image, comprising a non-transitory tangible computer-readable medium having computer-readable instructions thereon, the computer-readable instructions being executable by a processor to cause the processor to perform:

• obtaining a pair of a training image having a first degree of sharpness and a reference image having a second degree of sharpness, at least portions of the training image and the reference image in a same pair having same contents;
• inputting the training image to the image-enhancing convolutional neural network to generate a training enhanced image;
• inputting the training enhanced image into an edge detector;
• generating, by the edge detector, a plurality of first edge maps;
• inputting the reference image into the edge detector;
• generating, by the edge detector, a plurality of second edge maps;
• calculating one or more first losses based on the plurality of first edge maps and the plurality of second edge maps, a respective one of the one or more first losses being calculated based on a respective one of the plurality of first edge maps and a respective one of the plurality of second edge maps, the respective one of the plurality of first edge maps and the respective one of the plurality of second edge maps having a same scale;
• and
• tuning parameters in the image-enhancing convolutional neural network to minimize at least the one or more first losses.