Pre-organizing Shape Instances for Landmark-Based Shape Correspondence

Abstract

The major challenge in constructing a statistical shape model for a structure is shape correspondence, which identifies a set of corresponded landmarks across a population of shape instances to accurately estimate the underlying shape variation. Both global or pairwise shapecorrespondence methods have been developed to automatically identify the corresponded landmarks. For global methods, landmarks are found by optimizing a comprehensive objective function that considers the entire population of shape instances. While global methods can produce very accurate shape correspondence, they tend to be very inefficient when the population size is large. For pairwise methods, all shape instances are corresponded to a given template independently. Therefore, pairwise methods are usually very efficient. However, if the population exhibits a large amount of shape variation, pairwise methods may produce very poor shape correspondence. In this paper, we develop a new method that attempts to address the limitations of global and pairwise methods. In particular, we first construct a shape tree to globally organize the population of shape instances by identifying similar shape instance pairs. We then perform pairwise shape correspondence between such similar shape instances with high accuracy. Finally, we combine these pairwise correspondences to achieve a unified correspondence for the entire population of shape instances. We evaluate the proposed method by comparing its performance to five available shape correspondence methods, and show that the proposed method achieves the accuracy of a global method with the efficiency of a pairwise method.

Predict brain MR image registration via sparse learning of appearance and transformation

“…The high inter-image variation could potentially hinder the registration of two images (Jia et al, 2012a; Munsell et al, 2012). For example, in order to register the non-root images with the root directly (i.e., via state-of-the-art methods), we should better utilize the distribution of the dataset (i.e., in the tree structure) and acquire the transformation fields for the non-root images recursively.…”

“…First , the image guidance to the registration of the specific subject image can be acquired by cherry-picking the intermediate image with the most similar appearances to the subject (Dalal et al, 2010; Hamm et al, 2010; Jia et al, 2011; Munsell et al, 2012; Wolz et al, 2010). The subject can register with the selected intermediate image, and then borrow the pre-existing transformation field that deforms the intermediate image to the template.…”

Dense 3D Face Correspondence

“…However, this approach essentially ignores the proximity between the face instances and the global information underlying the population. Following Munsell et al [38], we address this issue by pre-organizing the faces using a minimum spanning tree. Let G " pV g , E g q be a directed graph where each node V g is a 3D face F from the training set and each edge E g connects two nodes pv i , v j q in the graph.…”

Perception-based shape retrieval for 3D building models

“…With this in mind, Temlyakov et al (2010), Xu et al (2009), Gopalan et al (2010), Yang and Latecki (2011) and Munsell et al (2012) have developed algorithms for improving the performance of shape retrieval. Moreover, there are numerous retrieval researches worldwide aimed at developing search engines for variously specialized 3D shapes.…”