A method and apparatus for combining a three-dimensional (3D) model with a plurality of two-dimensional (2D) images by adjusting degrees of transparency of the plurality of 2D images. The method includes: obtaining a plurality of 2D images; arranging the plurality of 2D images in a 3D space based on predetermined criteria; obtaining spatial coordinates of each of the plurality of 2D images arranged in the 3D space; generating a 3D model of the plurality of 2D images arranged in the 3D space based on the spatial coordinates; changing attribute information of the plurality of 2D images arranged in the 3D space; and displaying the 3D model and the plurality of 2D images whose attribute information is changed.