A Range Image Refinement Technique for Multi-view 3D Model Reconstruction

This paper presents 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. This paper introduces a range image refinement technique to correct such erroneous ranges by employing epipolar geometry of a multiview modeling 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 inverseprojections 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 correspondenc...

• Type: Conference
• Year: 2003
• Where: 3DIM
• Authors: Soon-Yong Park, Murali Subbarao
• Keywords: 3DIM 2003, Image Processing, Image Refinement Technique, Range Image Refinement, Range Images