Electronic apparatus and method for upscaling a down-scaled image by selecting an improved filter set for an artificial intelligence model
A method for controlling an electronic apparatus according to the disclosure includes receiving image data and information associated with a filter set that is applied to an artificial intelligence model for upscaling the image data from an external server; decoding the image data; upscaling the decoded image data using a first artificial intelligence model that is obtained based on the information associated with the filter set; and providing the upscaled image data for output.
1. A method for controlling an electronic apparatus, the method comprising:
receiving image data, an artificial intelligence (AI) flag indicating whether AI downscaling is performed by an external server, and a filter index from the external server;
decoding the image data;
in response to the AI flag being a first value and the filter index being not null, upscaling the decoded image data using a first AI model corresponding to the filter index and providing the upscaled image data for output;
in response to the AI flag being the first value and the filter index being null, upscaling the decoded image data using a default AI model and providing the upscaled image data for output; and
in response to the AI flag being not the first value, providing the decoded image data for output without performing an upscaling process,
wherein the image data is obtained by encoding downscaled image data acquired by inputting original image data corresponding to the image data into a second AI model for downscaling original image data,
wherein a number of filters of the first AI model is smaller than a number of filters of the second AI model, and
wherein the first AI model is a Convolutional Neural Network (CNN).
2. The method of claim 1 , wherein the providing comprises displaying the upscaled image data.
3. An electronic apparatus comprising:
a communication interface comprising communication circuitry; and
a processor that is configured to:
receive image data, an artificial intelligence (AI) flag indicating whether AI downscaling is performed by an external server, and a filter index from the external server via the communication interface;
decode the received image data;
in response to the AI flag being a first value and the filter index being not null, upscale the decoded image data using a first AI model corresponding to the filter index and provide the upscaled image data for output;
in response to the AI flag being the first value and the filter index being null, upscale the decoded image data using a default AI model and provide the upscaled image data for output; and
in response to the AI flag being not the first value, provide the decoded image data for output without performing an upscaling process,
wherein the image data is obtained by encoding downscaled image data acquired by inputting original image data corresponding to the image data into a second AI model for downscaling original image data,
wherein a number of filters of the first AI model is smaller than a number of filters of the second AI model, and
wherein the first AI model is a Convolutional Neural Network (CNN).
4. The electronic apparatus of claim 3 , further comprising:
a display,
wherein the processor is configured to provide the upscaled image data for output by controlling the display to display the upscaled image data.