The wave kernel signature: A quantum mechanical approach to shape analysis

Mathieu Aubry, Ulrich Schlickewei, Daniel Cremers
2011 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)  
We introduce the Wave Kernel Signature (WKS) for characterizing points on non-rigid three-dimensional shapes. The WKS represents the average probability of measuring a quantum mechanical particle at a specific location. By letting vary the energy of the particle, the WKS encodes and separates information from various different Laplace eigenfrequencies. This clear scale separation makes the WKS well suited for a large variety of applications. Both theoretically and in quantitative experiments we
more » ... demonstrate that the WKS is substantially more discriminative and therefore allows for better feature matching than the commonly used Heat Kernel Signature (HKS). As an application of the WKS in shape analysis we show results on shape matching.
doi:10.1109/iccvw.2011.6130444 dblp:conf/iccvw/AubrySC11 fatcat:lamjjf7cgja3tieoqgtwrvap4m