Anisotropic Laplace-Beltrami Operators for Shape Analysis

80 citations recorded by the source corpus.

How researchers see this paper

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

Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, methodology): “[7] used anisotropic heat kernels [1] as an alternative way of extracting intrinsic patches”
Geometric Deep Learning: Going beyond Euclidean data (2016, background): “involves the thermal conductivity tensor A(x) (in case of twodimensional manifolds, a 2× 2 matrix applied to the intrinsic gradient in the tangent plane at each point), allowing modeling heat flow that is position- and direction-dependent [82].”
Learning shape correspondence with anisotropic convolutional neural networks (2016, background): “[1] considered anisotropic diffusion driven by the surface curvature.”
Surface Networks (2017, background): “Although in general graphs there is no well-defined procedure to recover anisotropic local variations, in the case of surfaces some authors ([4, 1, 27]) have considered anisotropic extensions.”
Anisotropic Diffusion Descriptors (2016, methodology): “The construction of anisotropic Laplacians driven by principal curvatures was shown in [ARAC14] on meshes and in [KTT13] for abstract high-dimensional data.”
Geometric deep learning (2016, methodology): “This more general diffusion model was considered in [4] for shape analysis tasks.”