Geometrical cloning of 3D objects via simultaneous registration of multiple range images

TLDR: This work presents a method for the reconstruction of real-world objects from multiple range images based on a least-squares approach where a distance metric between the overlapping range images is minimized and a resolution hierarchy accelerates the registration substantially.

Abstract: Presents a method for the reconstruction of real-world objects from multiple range images. One major contribution of our approach is the simultaneous registration of all range images acquired from different scanner views. Thus, registration errors are not accumulated, and it is even possible to reconstruct large objects from an arbitrary number of small range images. The registration process is based on a least-squares approach where a distance metric between the overlapping range images is minimized. A resolution hierarchy accelerates the registration substantially. After registration, a volumetric model of the object is carved out. This step is based on the idea that no part of the object can lie between the measured surface and the camera of the scanner. With the marching cube algorithm, a polygonal representation is generated. The accuracy of this polygonal mesh is improved by moving the vertices of the mesh on to the surface implicitly defined by the registered range images.