In an image generation apparatus, an image acquisition unit is configured to acquire, from at least one camera operable to capture an image of surroundings of a vehicle, a captured image. A bird's-eye view image generation unit is configured to generate a bird's-eye view image from the captured image. A three-dimensional object recognition unit is configured to recognize a three-dimensional object in the captured image. A superimposition-image acquisition unit is configured to acquire a superimposition image that represents the three-dimensional object recognized by the three-dimensional object recognition unit, by performing a process depending on a type of the three-dimensional object recognized by the three-dimensional object recognition unit. A superimposition unit is configured to superimpose, onto the bird's-eye view image, the superimposition image acquired by the superimposition-image acquisition unit, at a position where the three-dimensional object is present in the bird's-eye view image.