3D reconstruction quality assessment using 2D reprojection with dynamic partitioning

Abstract

ABSTRACT In 3D reconstruction the stereo technique is one of the most used, generating point clouds of acceptable quality. One way to improve its quality is by fusing it with active systems such as lasers. For this fusion, a registration process can be used. It is important to evaluate the quality of the reconstruction in terms of spatial structure accuracy and visual appearance. A method of evaluating the quality of an active 3D stereo reconstruction is proposed, which takes a stereo camera image and compares it with a reprojected image of the registered cloud. The typical way of comparing two images calculates the point-to-point error, but does not take into account other aspects. Several quality metrics are studied to select the one that contributes the most in a given 3D reconstruction context. To improve the computational cost, a process of partitioning the images by regions is performed. A Quadtree partition was chosen with a homogeneity criterion that is selected among several criteria. The experiments and results for selecting the quality metric and the homogeneity criterion for the Quadtree partition are presented.