This paper proposes an effective method to synthesize arbitrary viewpoint images for the object with concavo-convex shape by constructing a 3D model from multi-view images. In the proposed method, a field which should be deformed in the 3D model is calculated with Block Space Carving method based on Space Carving method. In addition, the proposed method synthesizes 2D images at the camera positions that captured photographs and acquires robust evaluation objects for the 3D model. The proposed method constructs the 3D model considering concavo-convex shape by deforming the 3D model in the field while comparing 2D images with the photographs. At the end of this paper, the results of the simulation experiments with synthesizing arbitrary viewpoint images show that the proposed method is effective.