The ICP (Iterative Closest Point) algorithm is widely used for geometric alignment of three-dimensional models when an initial estimate of the relative pose is known. Many variants of ICP have been proposed, affecting all phases of the algorithm from the selection and matching of points to the minimization strategy. We enumerate and classify many of these variants, and evaluate their effect on the speed with which the correct alignment is reached. In order to improve convergence for nearly-flat meshes with small features, such as inscribed surfaces, we introduce a new variant based on uniform sampling of the space of normals. We conclude by proposing a combination of ICP variants optimized for high speed. We demonstrate an implementation that is able to align two range images in a few tens of milliseconds, assuming a good initial guess. This capability has potential application to real-time 3D model acquisition and model-based tracking.

In this paper we present a multiview registration method for aligning range data. We first align scans pairwise with each other and use the pairwise alignments as constraints that the multiview step enforces while evenly diffusing the pairwise registration errors. This approach is especially suitable for registering large data sets, since using constraints from pairwise alignments does not require loading the entire data set into memory to perform the alignment. The alignment method is efficient, and it is less likely to get stuck into a local minimum than previous methods, and can be used in conjunction with any pairwise method based on aligning overlapping surface sections.

This paper describes a method of automatically performing the registration of two range images that have signi#cant overlap. We #rst #nd points of interest in the intensity data that comes with each range image. Then we perform a triangulation of the 3D range points associated with these 2D interest points. All possible pairs of triangles between the two 3D triangulations are then matched. The fact that we have 3D data available makes it possible to e#ciently prune matches. We do this pruning by using a simple and e#ective set of compatibility tests between potentially matching triangles and vertices. The best match is the one that aligns the largest number of interest points between the two range images. The algorithms are demonstrated experimentally on a number of di#erent range image pairs.

Abstract not found

We propose a novel algorithm to register multiple 3D point sets within a common reference frame using a manifold optimization approach. The point sets are obtained with multiple laser scanners or a mobile scanner. Unlike most prior algorithms, our approach performs an explicit optimization on the manifold of rotations, allowing us to formulate the registration problem as an unconstrained minimization on a constrained manifold. This approach exploits the Lie group structure of SO3 and the simple representation of its associated Lie algebra so3 in terms of R 3. Our contributions are threefold. We present a new analytic method based on singular value decompositions that yields a closed-form solution for simultaneous multiview registration in the noise-free scenario. Secondly, we use this method to derive a good initial estimate of a solution in the noise-free case. This initialization step may be of use in any general iterative scheme. Finally, we present an iterative scheme based on Newton’s method on SO3 that has locally quadratic convergence. We demonstrate the efficacy of our scheme on scan data taken both from the Digital Michelangelo project and from scans extracted from models, and compare it to some of the other well known schemes for multiview registration. In all cases, our algorithm converges much faster than the other approaches, (in some cases orders of magnitude faster), and generates consistently higher quality registrations.

In this paper, we report on recent extensions to a surface matching algorithm based on local 3-D signatures. This algorithm was previously shown to be effective in view registration of general surfaces and in object recognition from 3-D model data bases. We describe extensions to the basic matching algorithm which will enable it to address several challenging, and often overlooked, problems encountered with real data. First, we describe extensions that allow us to deal with data sets with large variations in resolution and with large data sets for which computational efficiency is a major issue. The applicability of the enhanced matching algorithm is illustrated by an example application: the construction of large terrain maps and the construction

The problem of building virtual models from sensor data increases in importance as powerful graphics rendering hardware becomes widespread. Model building stands at the interface between computer vision and computer graphics, and researchers from both areas have made contributions. We believe that only by a systematic review of the remaining open research question can further progress be made. This paper is an attempt at providing such a review. First, we describe the basic steps in the model building pipeline. Then we discuss the open problems that remain in each step. Finally, we describe some overall research themes that we believe should guide further work in this area.

Abstract — The registration of full 3-D models is an important task in computer vision. Range finders only let to reconstruct a partial view of the object. The last years, many authors have proposed several techniques to register 3D surfaces from multiple views in which there are basically two aspects to consider. First, poor registration in which some sort of correspondences are established. Second, accurate registration in order to obtain a better solution. In this paper, a survey of the most common techniques is presented and includes experimental results of some of them. I.

Abstract not found

Building of three-dimensional models is an important topic in computer vision. Range finders only let to reconstruct a partial view of the object. However, in most part of applications a full reconstruction is required. Many authors have proposed several techniques to register 3D surfaces from multiple views. In this paper, a survey of the most common techniques is presented. Furthermore experimental results are performed, and a 3D model is obtained.