Skip to yearly menu bar Skip to main content


Poster

Learning shape correspondence with anisotropic convolutional neural networks

Davide Boscaini · Jonathan Masci · Emanuele RodolĂ  · Michael Bronstein

Area 5+6+7+8 #165

Keywords: [ Deep Learning or Neural Networks ] [ (Application) Computer Vision ]


Abstract:

Convolutional neural networks have achieved extraordinary results in many computer vision and pattern recognition applications; however, their adoption in the computer graphics and geometry processing communities is limited due to the non-Euclidean structure of their data. In this paper, we propose Anisotropic Convolutional Neural Network (ACNN), a generalization of classical CNNs to non-Euclidean domains, where classical convolutions are replaced by projections over a set of oriented anisotropic diffusion kernels. We use ACNNs to effectively learn intrinsic dense correspondences between deformable shapes, a fundamental problem in geometry processing, arising in a wide variety of applications. We tested ACNNs performance in very challenging settings, achieving state-of-the-art results on some of the most difficult recent correspondence benchmarks.

Live content is unavailable. Log in and register to view live content