It is required to carry out a tapping operation on a display screen to adjust the focus in a case where refocus process is performed in shifting to a reproduction mode, so that a user has to do an extra work. An image processing apparatus obtains a multi-view image data obtained by image-capturing in a plurality of viewpoints. A mode indicating information on a target to be focused is set. A combined image data focused on the target is generated by executing image processing to the multi-view image data based on the set mode.