Image processing apparatus, image processing method and storage medium

An image processing method that uses a first image group to make an image of a second image group with fewer high frequency components than an image of the first image group high definition, comprising:

• selecting, on a basis of a current image selected as a high definition target from the second image group, teacher data to be used in learning from among a plurality of teacher data which use an image included in the first image group as one of a pair of images;
• calculating a degree of similarity with a partial region corresponding to a previous image which is a high definition target selected from the second image group previous to the current image selected as the high definition target from the second image group for each one of a plurality of partial regions obtained by dividing the current image selected as the high definition target from the second image group;
• determining a plurality of local regions from the current image by combining a collection of one or more partial regions with the degree of similarity equal to or greater than a threshold as one local region, and treating a partial region with the degree of similarity less than the threshold as a separate local region;
• generating a learning model for inference of high frequency components using teacher data selected in the selecting for each one of the plurality of local regions;
• inferring high frequency components using the learning model for each one of the plurality of local regions;
• and
• generating a high definition image on a basis of the current image and the high frequency components inferred in the inferring,
• wherein the first image group and the second image group are both moving image content, and the previous image selected from the second image group and the current image selected from the second image group are both frames of the moving image content.

A non-transitory computer-readable storage medium storing a program for causing a computer to execute an image processing method that uses a first image group to make an image of a second image group with fewer high frequency components than an image of the first image group high definition, the method comprising:

• selecting, on a basis of a current image selected as a high definition target from the second image group, teacher data to be used in learning from among a plurality of teacher data which use an image included in the first image group as one of a pair of images;
• calculating a degree of similarity with a partial region corresponding to a previous image which is a high definition target selected from the second image group previous to the current image selected as the high definition target from the second image group for each one of a plurality of partial regions obtained by dividing the current image selected as the high definition target from the second image group;
• determining a plurality of local regions from the current image by combining a collection of one or more partial regions with the degree of similarity equal to or greater than a threshold as one local region, and treating a partial region with the degree of similarity less than the threshold as a separate local region;
• generating a learning model for inference of high frequency components using teacher data selected in the selecting for each one of the plurality of local regions;
• inferring high frequency components using the learning model for each one of the plurality of local regions;
• and
• generating a high definition image on a basis of the current image and the high frequency components inferred in the inferring,
• wherein the first image group and the second image group are both moving image content, and the previous image selected from the second image group and the current image selected from the second image group are both frames of the moving image content.