Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs
A common approach to define convolutions on meshes is to interpret them as a graph and apply graph convolutional networks (GCNs). Such GCNs utilize isotropic kernels and are therefore insensitive to the relative orientation of vertices and thus to the geometry of the mesh as a whole. We propose Gauge Equivariant Mesh CNNs which generalize GCNs to apply anisotropic gauge equivariant kernels. Since the resulting features carry orientation information, we introduce a geometric message passing scheme defined by parallel transporting features over mesh edges. Our experiments validate the significantly improved expressivity of the proposed model over conventional GCNs and other methods.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Gauge Equivariant Spherical CNNs
Spherical CNNs are convolutional neural networks that can process signals on the sphere, such as global climate and weather patterns or omnidirectional images. Over the last few years, a number of spherical convolution m…
Semantic SegmentationGeometrical aspects of lattice gauge equivariant convolutional neural networks
Lattice gauge equivariant convolutional neural networks (L-CNNs) are a framework for convolutional neural networks that can be applied to non-Abelian lattice gauge theories without violating gauge symmetry. We demonstrat…
A Functional Approach to Rotation Equivariant Non-Linearities for Tensor Field Networks.
Learning pose invariant representation is a fundamental problem in shape analysis. Most existing deep learning algorithms for 3D shape analysis are not robust to rotations and are often trained on synthetic datasets …
Higher Order Gauge Equivariant CNNs on Riemannian Manifolds and Applications
With the advent of group equivariant convolutions in deep networks literature, spherical CNNs with $\mathsf{SO}(3)$-equivariant layers have been developed to cope with data that are samples of signals on the sphere $S^2$…
Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds
Motivated by the vast success of deep convolutional networks, there is a great interest in generalizing convolutions to non-Euclidean manifolds. A major complication in comparison to flat spaces is that it is unclear in …