Learning device, image generating device, learning method, image generating method, and program

A method of image generation performed by an electronic device, the method comprising:

• obtaining a target input image having a first angle of view;
• performing semantic segmentation on the target input image to generate result data,
• wherein the semantic segmentation performed on the target input image comprises a learned semantic segmentation that is based on first learning data that comprises a first learning input image and teacher data;
• generating input data obtained by coupling the target input image and the result data to each other;
• performing image generation, in response to the input data, of a second image having a second angle of view wider than the first angle of view;
• and
• displaying the second image,
• wherein the image generation performed on the input data comprises a learned image generation that is based on second learned data that comprises a second learning input image and a learning wide view angle image, and
• wherein the second image having the second angle of view is generated based on the target image having the first angle of view and an estimate of an environment outside of the first angle of view of the target image.

A non-transitory computer readable medium containing instructions to cause a computer to perform a method of image generation, the method comprising:

• obtaining a target input image having a first angle of view;
• performing semantic segmentation on the target input image to generate result data,
• wherein the semantic segmentation performed on the target input image comprises a learned semantic segmentation that is based on first learning data that comprises a first learning input image and teacher data;
• generating input data obtained by coupling the target input image and the result data to each other;
• performing image generation, in response to the input data, of a second image having a second angle of view wider than the first angle of view;
• and
• displaying the second image,
• wherein the image generation performed on the input data comprises a learned image generation that is based on second learned data that comprises a second learning input image and a learning wide view angle image, and
• wherein the second image having the second angle of view is generated based on the target image having the first angle of view and an estimate of an environment outside of the first angle of view of the target image.