3D modeling using hierarchical feature point and spatio-temporal relationship

This paper proposes a new 3D modeling technique based on feature points using spatio-temporal relationship. Normally, the generation of a 3D model from a real scene requires the computation of the depth of the model vertices from a dense correspondence map of the whole image. This is very time consuming, plus it is also quite difficult to achieve an accurate depth. The proposed method can generate a 3D model of an object based on identifying the correspondence of certain feature points without the need for a dense correspondence map. The proposed method consists of three parts: the extraction of an object, the extraction of feature points, and hierarchical 3D modeling using the classified feature points. This method is effective in generating a 3D model and expressing the smoothness of plain regions and sharpness of edges.