Anisotropic diffusion descriptors

Boscaini D, Masci J, Rodola E, Bronstein MM, Cremers D (2016)

Publication Type: Journal article

Publication year: 2016

Journal

Computer Graphics Forum Wiley-Blackwell

Book Volume: 35

Pages Range: 431-441

Journal Issue: 2

DOI: 10.1111/cgf.12844

Abstract

Spectral methods have recently gained popularity in many domains of computer graphics and geometry processing, especially shape processing, computation of shape descriptors, distances, and correspondence. Spectral geometric structures are intrinsic and thus invariant to isometric deformations, are efficiently computed, and can be constructed on shapes in different representations. A notable drawback of these constructions, however, is that they are isotropic, i.e., insensitive to direction. In this paper, we show how to construct direction-sensitive spectral feature descriptors using anisotropic diffusion on meshes and point clouds. The core of our construction are directed local kernels acting similarly to steerable filters, which are learned in a task-specific manner. Remarkably, while being intrinsic, our descriptors allow to disambiguate reflection symmetries. We show the application of anisotropic descriptors for problems of shape correspondence on meshes and point clouds, achieving results significantly better than state-of-the-art methods.

Involved external institutions

Università della Svizzera italiana (USI)

Switzerland (CH) Technische Universität München (TUM)

Germany (DE)

How to cite

APA:

Boscaini, D., Masci, J., Rodola, E., Bronstein, M.M., & Cremers, D. (2016). Anisotropic diffusion descriptors. Computer Graphics Forum, 35(2), 431-441. https://dx.doi.org/10.1111/cgf.12844

MLA:

Boscaini, Davide, et al. "Anisotropic diffusion descriptors." Computer Graphics Forum 35.2 (2016): 431-441.

BibTeX: Download