A range image refinement technique for multi-view 3D model reconstruction

We present a range image refinement technique for generating accurate 3D computer models of real objects. Range images obtained from a stereo-vision system typically experience geometric distortions on reconstructed 3D surfaces due to the inherent stereo matching problems such as occlusions or mismatchings. We introduce a range image refinement technique to correct such erroneous ranges by employing epipolar geometry of a multiview modelling system and the visual hull of an object. After registering multiple range images into a common coordinate system, we first determine if a 3D point in a range image is erroneous, by measuring registration of the point with its correspondences in other range images. The correspondences are determined on 3D contours which are inverse-projections of epipolar lines in other 2D silhouette images. Then the range of the point is refined onto the object's surface, if it is erroneous. We employ two techniques to search the correspondences fast. In case that there is no correspondence for an erroneous point, we refine the point onto the visual hull of the object. We show that refined range images yield better geometric structures in reconstructed 3D models.