17/08/2020

CNNs on surfaces using rotation-equivariant features

Ruben Wiersma, Elmar Eisemann, Klaus Hildebrandt

Keywords: shape classification, shape segmentation, shape correspondence, surface networks, CNNs on surfaces, circular Harmonic Filters, geometric deep learning, rotation-equivariance

Abstract Paper Similar Papers

Abstract: This paper is concerned with a fundamental problem in geometric deep learning that arises in the construction of convolutional neural networks on surfaces. Due to curvature, the transport of filter kernels on surfaces results in a rotational ambiguity, which prevents a uniform alignment of these kernels on the surface. We propose a network architecture for surfaces that consists of vector-valued, rotation-equivariant features. The equivariance property makes it possible to locally align features, which were computed in arbitrary coordinate systems, when aggregating features in a convolution layer. The resulting network is agnostic to the choices of coordinate systems for the tangent spaces on the surface. We implement our approach for triangle meshes. Based on circular harmonic functions, we introduce convolution filters for meshes that are rotation-equivariant at the discrete level. We evaluate the resulting networks on shape correspondence and shape classifications tasks and compare their performance to other approaches.

The video of this talk cannot be embedded. You can watch it here:
https://dl.acm.org/doi/10.1145/3386569.3392437#sec-supp
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at SIGGRAPH 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 3:08 
 0
 0
 0
 0
 19:33 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 0:58 
 0
 0
 0
 0
 3:04 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 12:13 
 0
 0
 0
 0
 10:41 
 0
 0
 0
 0
 13:04 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 2:43 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 4:09 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 16:11 
 0
 0
 0
 1
 5:10 
 0
 0
 0
 1
 15:56 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 4:53 
 0
 0
 0
 0
 9:36 
 0
 0
 0
 0
 2:58 
 0
 0
 0
 0
 9:24 
 0
 0
 0
 0
 13:43 
 0
 0
 0
 0
 18:37 
 0
 0
 0
 0
 14:44 
 0
 0
 0
 0
 13:19 
 0
 0
 0
 0
 5:08 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 14:50 
 0
 0
 0
 0
 15:58 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 12:20 
 0
 0
 0
 0
 8:40 
 0
 0
 0
 0
 12:11 
 0
 0
 0
 0
 3:04