Similarity of Deforming Meshes Based on Spatio-temporal Segmentation

Abstract

In this study, we investigate a similarity metric for comparing two deforming meshes. While there have been a large body of works on computing the similarity of static shapes, similarity judgments on deforming meshes are not studied well. Our algorithm uses the degree of deformation to binarily label each triangle in deforming mesh in the spatio-temporal domain, which serves as basis for the spatio-temporal segmentation. The segmentation results are encoded in a form of evolving graph, with an aim of obtaining a compact representation of the motion of the mesh. Finally, we formulate the similarity computation as a sequence matching problem: After clustering similar graphs and assigning each of the graphs with the cluster labels, each deforming mesh is represented with a sequence of labels. Then, we apply a sequence alignment algorithm to compute the locally optimal alignment between the two cluster label sequences, and to compute the similarity metric by normalizing the alignment score. We show that similarities of animation data can be captured correctly by our approach. This may be significant, as it solves a problem that cannot be handled by current approaches.