Surface matching using consistent pants decomposition

TL;DR: A powerful pants decomposition framework for computing maps between surfaces with arbitrary topologies that is more intuitive, less labor-intensive, and requires no user's expertise in computing complicated surface map between arbitrary shapes is developed.

Abstract: Surface matching is fundamental to shape computing and various downstream applications. This paper develops a powerful pants decomposition framework for computing maps between surfaces with arbitrary topologies. We first conduct pants decomposition on both surfaces to segment them into consistent sets of pants patches (here a pants patch is intuitively defined as a genus-zero surface with three boundaries). Then we compose global mapping between two surfaces by harmonic maps of corresponding patches. This framework has several key advantages over other state-of-the-art techniques. First, the surface decomposition is automatic and general. It can automatically construct mappings for surfaces with same but complicated topology, and the result is guaranteed to be one-to-one continuous. Second, the mapping framework is very flexible and powerful. Not only topology and geometry, but also the semantics can be easily integrated into this framework with a little user involvement. Specifically, it provides an easy and intuitive human-computer interaction mechanism so that mapping between surfaces with different topologies, or with additional point/curve constraints, can be properly obtained within our framework. Compared with previous user-guided, piecewise surface mapping techniques, our new method is more intuitive, less labor-intensive, and requires no user's expertise in computing complicated surface map between arbitrary shapes. We conduct various experiments to demonstrate its modeling potential and effectiveness.