Bayesian Inference of Bijective Non-Rigid Shape Correspondence

By Matthias Vestner, Roee Litman, A. Bronstein, Emanuele Rodolà, Daniel Cremers. 2016

11 citations recorded by the source corpus.

Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space. Such are, for example, various point-wise correspondence recovery algorithms used as a postprocessing stage in the functional correspondence framework. In this paper, we show that such frequently used techniques in practice suffer from lack of accuracy and result in poor surjectivity. We propose an alternative recovery technique guaranteeing a bijective correspondence and producing significantly higher accuracy. We derive the proposed method from a statistical framework of Bayesian inference and demonstrate its performance on several challenging deformable 3D shape matching datasets.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Geometry and Topology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Geometry and Topology

Citations in the corpus

Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, methodology): “48% 78.81 0.44% in all the poses were used for training (800 shapes in total); the remaining 20 subjects were used for testing. The output of the network was reﬁned using the intrinsic Bayesian ﬁlter [55] in order to remove some local outliers. Correspondence quality was evaluated using the Princeto”