J
Jan Eric Lenssen
Researcher at Technical University of Dortmund
Publications - 27
Citations - 4680
Jan Eric Lenssen is an academic researcher from Technical University of Dortmund. The author has contributed to research in topics: Deep learning & Equivariant map. The author has an hindex of 12, co-authored 24 publications receiving 2223 citations.
Papers
More filters
Posted Content
Fast Graph Representation Learning with PyTorch Geometric
Matthias Fey,Jan Eric Lenssen +1 more
TL;DR: PyTorch Geometric is introduced, a library for deep learning on irregularly structured input data such as graphs, point clouds and manifolds, built upon PyTorch, and a comprehensive comparative study of the implemented methods in homogeneous evaluation scenarios is performed.
Journal ArticleDOI
Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks
Christopher Morris,Martin Ritzert,Matthias Fey,William L. Hamilton,Jan Eric Lenssen,Gaurav Rattan,Martin Grohe +6 more
TL;DR: In this article, a generalization of GNNs, called k-dimensional GNN (k-GNNs), is proposed, which can take higher-order graph structures at multiple scales into account.
Posted Content
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
Christopher Morris,Martin Ritzert,Matthias Fey,William L. Hamilton,Jan Eric Lenssen,Gaurav Rattan,Martin Grohe +6 more
TL;DR: In this article, a generalization of GNNs, called $k$-dimensional GNN, was proposed, which can take higher-order graph structures at multiple scales into account.
Proceedings ArticleDOI
SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
TL;DR: This work presents Spline-based Convolutional Neural Networks (SplineCNNs), a variant of deep neural networks for irregular structured and geometric input, e.g., graphs or meshes, that is a generalization of the traditional CNN convolution operator by using continuous kernel functions parametrized by a fixed number of trainable weights.
Book ChapterDOI
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
Rohan Chabra,Jan Eric Lenssen,Eddy Ilg,Tanner Schmidt,Julian Straub,Steven Lovegrove,Richard Newcombe +6 more
TL;DR: Deep Local Shapes (DeepLS) as discussed by the authors replaces the dense volumetric signed distance function (SDF) representation used in traditional surface reconstruction systems with a set of locally learned continuous SDFs defined by a neural network.