A depth map generation device for merging multiple depth maps includes two image capturers, a depth map generator, and a mixer. The two image capturers are used for generating two first images. The depth map generator is coupled to the two image capturers, wherein the depth map generator generates a first depth map and a second depth map according to the two first images. The mixer is coupled to the depth map generator for merging the first depth map and the second depth map to generate a final depth map, wherein the first depth map and the second depth map have different characteristics.