An image processing device combines a plurality of time-series images to generate a composite image with a higher resolution than a resolution of the plurality of images. The image processing device includes a processor that includes hardware and that is configured to: detect depth information of at least one image of the plurality of images; and set the number of images to be combined for generating the composite image on the basis of the detected depth information. The depth information indicates a depth of a captured scene of the at least one image. The processor is configured to reduce the number of images as the depth of the captured scene increases.