Abstract

We propose a shape matching method that produces dense correspondences tuned to a specifific class of shapes and deformations. In a scenario where this class is represented by a small set of example shapes, the proposed method learns a shape descriptor capturing the variability of the deformations in the given class. The approach enables the wave kernel signature to extend the class of recognized deformations from near isometries to the deformations appearing in the example set by means of a random forest classififier. With the help of the introduced spatial regularization, the proposed method achieves signifificant improvements over the baseline approach and obtains stateof-the-art results while keeping short computation times.