An electronic device according to an embodiment of this document, may include a camera module supporting an auto focus (AF) function, and at least one processor electrically connected to the camera module. The at least one processor may obtain a first image frame focusing on a first position from the camera module, obtain a second image frame following the first image frame from the camera module, perform deep learning on the first image frame and the second image frame, determine whether it is necessary to set the focus of the second image frame to a second position different from the first position based on a result of the deep learning, and control the AF function of the camera module according to the determination result.