An image processing device includes: an image acquisition section that acquires captured image data captured using an image sensor including color filters corresponding to bands, and corresponding to a plurality of frames; an alignment processing section that performs an alignment process on the captured image data to generate integrated captured image data; a reference band selection section that selects a reference band from the bands using an output image in a preceding frame; a reference image generation section that performs an interpolation process on image data included in the integrated captured image data and corresponding to the color filter corresponding to the reference band; and an interpolated image generation section that performs an interpolation process on image data included in the integrated captured image data and corresponding to the color filter corresponding to a band differing from the reference band based on a reference image to generate an interpolated image.