Fast and accurate triangular model generation for the shape-from-silhouette technique

In this study, we propose a method for generating triangular meshes of objects based on the shape-from-silhouette (SFS) technique. The proposed algorithm uses the direct intersection of multiple sets of infinite polygons from the silhouettes of two-dimensional (2D) images to acquire the surface points of an object. The surface points are then triangulated according to the topological relationship of the obtained points and the polygons corresponding to each of the points. In addition, a comprehensive study between the proposed method and the marching-cubes method was conducted. The main advantages of the proposed method are that all 3D points are precisely located on the silhouettes of 2D images, and that the number of vertices on the triangular model is very efficient compared to that for the results from the marching-cubes method. In contrast, the marching-cubes method faces noise and resolution problems, where the former is because the vertices are interpolated, and the latter is because the maximum level is restricted. Several realistic examples are presented to demonstrate the feasibility of the proposed method.