Automatic Correspondence for 3d Modeling: an Extensive Review

To generate a 3D computer model of a free-form object, multiple range images (point clouds) covering its entire surface are acquired from different viewpoints. These views are then aligned in a common coordinate basis by minimizing the distance error between their corresponding points. Establishing correspondences automatically is an inherently challenging problem due to the lack of any type of information other than the geometrical information extracted from the point clouds. Existing “automatic” correspondence techniques achieve automatism at the expense of other important specifications namely, applicability to free-form objects, accuracy, efficiency, robustness to resolution and surface sampling, robustness to overlap, robustness to noise and finally their applicability to simultaneous multiview correspondence. There is also a lack of a review paper that describes and critically analyzes these techniques. In this paper, we present such an extensive review and carry out the analysis of each technique according to the above listed indispensable criteria. Our analysis shows that none of these techniques fully meets these criteria and that there is still a need for the development of practical automatic correspondence algorithms.