Electronic apparatus, control method thereof and electronic system

An electronic apparatus comprising:

• a communication interface comprising circuitry;
• a memory configured to store an upscaling network of a first artificial intelligence model;
• a display;
• and
• a processor connected to the memory and the communication interface and configured to control the electronic apparatus,
• wherein the processor is configured to:
• receive an image from another electronic apparatus through the communication interface,
• obtain an output image in which the received image is upscaled by inputting the received image to the upscaling network, and
• control the display to display the output image,
• wherein the first artificial intelligence model is configured to be learned based on a sample image, a first intermediate image obtained by inputting the sample image to a downscaling network of the first artificial intelligence model, a first final image obtained by inputting the first intermediate image to the upscaling network of the first artificial intelligence model, a second intermediate image in which the sample image is downscaled by a legacy scaler, and a second final image in which the first intermediate image is upscaled by the legacy scaler,
• wherein the first artificial intelligence model is configured to be learned based on a weighted sum of a first difference between the sample image and the first final image, a second difference between the sample image and the second final image, a third difference between the first intermediate image and the second intermediate image.

A method of controlling an electronic apparatus comprising:

• obtaining an output image in which an input image is downscaled by inputting the input image to a downscaling network of a first artificial intelligence model;
• and
• transmitting the output image to another electronic apparatus,
• wherein the first artificial intelligence model is configured to be learned based on a sample image, a first intermediate image obtained by inputting the sample image to the downscaling network, a first final image obtained by inputting the first intermediate image to an upscaling network of the first artificial intelligence model, a second intermediate image in which the sample image is downscaled by a legacy scaler, and a second final image in which the first intermediate image is upscaled by the legacy scaler, and
• wherein the first artificial intelligence model is configured to be learned based on:
• a weighted sum of a first difference between the sample image and the first final image, a second difference between the sample image and the second final image, a third difference between the first intermediate image and the second intermediate image.