An Image Processing Approach to Surface Matching

Abstract

Establishing a correspondence between two surfaces is a basic ingredient in many geometry processing applications. Existing approaches, which attempt to match two meshes directly in 3D, can be cumbersome to implement and it is often hard to produce accurate results in a reasonable amount of time. In this paper, we present a new variational method for matching surfaces that addresses these issues. Instead of matching two surfaces directly in 3D, we apply well-established matching methods from image processing in the parameter domains of the surfaces. A matching energy is introduced that can depend on curvature, feature demarcations or surface textures, and a regularization energy controls length and area changes in the induced non-rigid deformation between the two surfaces. The metric on both surfaces is properly incorporated into the formulation of the energy. This approach reduces all computations to the 2D setting while accounting for the original geometries. Consequently a fast multiresolution numerical algorithm for regular image grids can be used to solve the global optimization problem. The final algorithm is robust, generically much simpler than direct matching methods, and very fast for highly resolved triangle meshes.