HalfedgeCNN for Native and Flexible Deep Learning on Triangle Meshes
Loading...
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
We describe HalfedgeCNN, a collection of modules to build neural networks that operate on triangle meshes. Taking inspiration from the (edge-based) MeshCNN, convolution, pooling, and unpooling layers are consistently defined on the basis of halfedges of the mesh, pairs of oppositely oriented virtual instances of each edge. This provides benefits over alternative definitions on the basis of vertices, edges, or faces. Additional interface layers enable support for feature data associated with such mesh entities in input and output as well. Due to being defined natively on mesh entities and their neighborhoods, lossy resampling or interpolation techniques (to enable the application of operators adopted from image domains) do not need to be employed. The operators have various degrees of freedom that can be exploited to adapt to application-specific needs.
Description
CCS Concepts: Computing methodologies -> Shape analysis; Mesh models; Neural networks
@article{10.1111:cgf.14898,
journal = {Computer Graphics Forum},
title = {{HalfedgeCNN for Native and Flexible Deep Learning on Triangle Meshes}},
author = {Ludwig, Ingmar and Tyson, Daniel and Campen, Marcel},
year = {2023},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.14898}
}