Device and method to generate image using image learning model
At least some example embodiments disclose a device and a method for generating a synthetic image and a different-angled image and eliminating noise. The method may include receiving input images, extracting feature values corresponding to the input images using an image learning model, the image learning model permitting an input and an output to be identical and generating a synthetic image based on the feature values corresponding to the input images using the image learning model.
1. A method of generating a different-angled image, the method comprising:
receiving input images and angle information;
combining feature values, wherein each of the feature values are extracted from a different corresponding input image among the input images;
generating a synthetic image from the combined feature values; and
generating an output image based on the synthetic image and the angle information using a trained image learning model, the generating including,
rotating an object by the angle to generate the output image, and
wherein the synthetic image includes the object and the angle information includes information associated with an angle for the object, and the output image includes the object.
2. The method of claim 1 , wherein the generating the output image comprises:
generating the output image by converting the synthetic image to correspond to the angle information using the image learning model.
3. The method of claim 1 , wherein the image learning model is trained in pairs of references images corresponding to different angles, and
the pairs of reference images comprise a first reference angle image corresponding to a first angle and a second reference angle image corresponding to a second angle, and
wherein the first reference angle image and the second reference angle image include an identical reference object.
4. The method of claim 3 , wherein the image learning model comprises a neural network, the neural network including at least one layer connected to another layer through a connection line, the connection line having a connection weight.
5. The method of claim 4 , wherein the connection weight of the neural network allows the second reference angle image to be output based on the second angle and the first reference angle image.
6. The method of claim 1 , wherein the object comprises a human face.
7. The method of claim 1 , wherein the trained image learning model permits an input and an output to be identical.
8. The method of claim 1 , wherein the generating the synthetic image includes using the trained image learning model.