• Publications
  • Influence
Laplacian surface editing
TLDR
Surface editing operations commonly require geometric details of the surface to be preserved as much as possible. Expand
Provably Powerful Graph Networks
TLDR
In search for more expressive graph learning models we build upon the recent k-order invariant and equivariant graph neural networks (Maron et al. 2019a,b) and present two results: First, we show that such k- order networks can distinguish between non-isomorphic graphs as good as the k-WL tests, which are provably stronger than the first WL test for k>2. Expand
Blended intrinsic maps
This paper describes a fully automatic pipeline for finding an intrinsic map between two non-isometric, genus zero surfaces. Our approach is based on the observation that efficient methods exist toExpand
Invariant and Equivariant Graph Networks
TLDR
We provide a characterization of all permutation invariant and equivariant linear layers for (hyper-)graph data, and show that their dimension, in case of edge-value graph data, is 2 and 15, respectively. Expand
Coordinates for instant image cloning
TLDR
We introduce an alternative, coordinate-based approach, where rather than solving a large linear system to perform the aforementioned interpolation, the value of the interpolant at each interior pixel is given by a weighted combination of values along the boundary. Expand
Blended intrinsic maps
TLDR
This paper describes a fully automatic pipeline for finding an intrinsic map between two non-isometric, genus zero surfaces. Expand
Differential coordinates for interactive mesh editing
TLDR
In this paper we advocate the use of linear differential coordinates as means to preserve the high-frequency detail of the surface by solving a linear least squares system. Expand
Comparing Dirichlet normal surface energy of tooth crowns, a new technique of molar shape quantification for dietary inference, with previous methods in isolation and in combination.
Inferred dietary preference is a major component of paleoecologies of extinct primates. Molar occlusal shape correlates with diet in living mammals, so teeth are a potentially useful structure fromExpand
Point convolutional neural networks by extension operators
TLDR
This paper presents Point Convolutional Neural Networks (PCNN): a novel framework for applying convolutional neural networks to point clouds. Expand
On the Universality of Invariant Networks
TLDR
Constraining linear layers in neural networks to respect symmetry transformations from a group $G$ is a common design principle for invariant networks that has found many applications in machine learning. Expand
...
1
2
3
4
5
...