Electronic device performing interpolation, operation method, and storage medium

A non-transitory storage medium storing at least one computer-readable instruction, the at least one computer-readable instruction, when executed by at least one processor of an electronic device, enabling the electronic device to perform at least one operation, the at least one operation comprising:

• obtaining a first image frame and a second image frame;
• identifying a first interpolation-applied object and a first interpolation non-applied object among objects included in the first image frame based on identifying a discontinuous map corresponding to the first image frame and the second image frame, and identifying a second interpolation-applied object and a second interpolation non-applied object among objects included in the second image frame,
• wherein the first interpolation-applied object and the second interpolation-applied object are objects having a gradually continuous movement in the first image frame and the second image frame, and
• wherein the first interpolation non-applied object and the second interpolation non-applied object are objects having no gradually continuous movement in the first image frame and the second image frame;
• and
• providing an interpolation image frame including a result of interpolation on the first interpolation-applied object and the second interpolation-applied object and the first interpolation non-applied object or the second interpolation non-applied object,
• wherein the discontinuous map includes information for identifying the first interpolation-applied object, the first interpolation non-applied object, the second interpolation-applied object, or the second interpolation non-applied object.

An electronic device comprising:

• at least one processor;
• and
• a memory,
• wherein the memory stores at least one instruction that, when executed by the at least one processor, enables the electronic device to:
• input a plurality of image frames to a first AI model and obtain a discontinuous map as an output from the first AI model,
• input a first image frame and a second image frame among the plurality of image frames to a second AI model for interpolation and obtain an interpolation image frame as an output from the second AI model, and
• provide a final interpolation image frame for the first image frame and the second image frame, based on a weighted sum of the interpolation image frame, the discontinuous map, and a reference image frame selected among the first image frame and the second image frame.