Information processing method, information processing system, and information processing apparatus

1. An information processing method executed by a computer, the information processing method comprising:

obtaining a first image generated by a multi-pinhole camera;

extracting at least one point spread function (PSF) in each of a plurality of regions in the first image;

obtaining a second image different from the first image, and reference data used in machine learning for the second image;

generating a third image, by convolving each of a plurality of regions in the second image with at least one PSF extracted in a corresponding region of the plurality of regions in the first image; and

outputting a pair of the reference data and the third image.

2. The information processing method according to claim 1 ,

wherein the at least one PSF extracted in each of the plurality of regions in the first image comprises a plurality of PSFs, and

a PSF with which each of the plurality of regions in the second image is convolved is selected from the plurality of PSFs.

3. The information processing method according to claim 2 ,

wherein a plurality of the second images are obtained, and

the PSF selected to convolve each of the plurality of regions in the second image is different between the plurality of the second images.

4. The information processing method according to claim 1 , comprising:

training an inference model by machine learning, using the third image as training data and the reference data.

5. The information processing method according to claim 1 ,

wherein the plurality of regions in the first image and the plurality of regions in the second image correspond one-to-one to each other.

6. The information processing method according to claim 1 ,

wherein the plurality of regions in the first image and the plurality of regions in the second image each include a plurality of pixels.

7. The information processing method according to claim 1 ,

wherein the second image is an image generated by a camera different from the multi-pinhole camera by which the first image is generated.

8. An information processing system, comprising:

a first obtainer that obtains a first image generated by a multi-pinhole camera;

a PSF extractor that extracts at least one point spread function (PSF) in each of a plurality of regions in the first image;

a second obtainer that obtains a second image different from the first image, and reference data used in machine learning for the second image;

an image generator that generates a third image, by convolving each of a plurality of regions in the second image with at least one PSF extracted in a corresponding region of the plurality of regions in the first image; and

an outputter that outputs a pair of the reference data and the third image.

9. An information processing apparatus, comprising:

an obtainer that obtains a fourth image;

a controller that inputs the fourth image to an inference model to obtain an inference result; and

an outputter that outputs data based on the inference result obtained,

wherein the inference model is trained using: reference data used in machine learning for a second image; and a third image as training data,

the third image is generated by convolving each of a plurality of regions in the second image with at least one point spread function (PSF) extracted in a corresponding region of a plurality of regions in a first image that is different from the second image, and

the first image is generated by a multi-pinhole camera.