Elastic convolved icp for the registration of deformable objects

This paper describes a method for registering de-formable 3D objects. When an object such as a hand de-forms, the deformation of the local shape is small, whereas the global shape deforms to a greater extent in many cases. Therefore, the local shape can be used as a feature for matching corresponding points. Instead of using a descrip-tor of the local shape, we introduce the convolution of the error between corresponding points for each vertex of a 3D mesh model. This approach is analogous to window match-ing in 2D image registration. Since the proposed method computes the convolution for every vertex in a model, it incorporates dense feature matching as opposed to sparse matching based on certain feature descriptors. Through ex-periments, we show that the convolution is useful for finding corresponding points and evaluate the accuracy of the reg-istration