DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds

Research output: Contribution to journalArticleScientificpeer-review

4 Citations (Scopus)
65 Downloads (Pure)

Abstract

Learning from 3D point-cloud data has rapidly gained momentum, motivated by the success of deep learning on images and the increased availability of 3D~data. In this paper, we aim to construct anisotropic convolution layers that work directly on the surface derived from a point cloud. This is challenging because of the lack of a global coordinate system for tangential directions on surfaces. We introduce DeltaConv, a convolution layer that combines geometric operators from vector calculus to enable the construction of anisotropic filters on point clouds. Because these operators are defined on scalar- and vector-fields, we separate the network into a scalar- and a vector-stream, which are connected by the operators. The vector stream enables the network to explicitly represent, evaluate, and process directional information. Our convolutions are robust and simple to implement and match or improve on state-of-the-art approaches on several benchmarks, while also speeding up training and inference.
Original languageEnglish
Article number105
Number of pages13
JournalACM Transactions on Graphics
Volume41
Issue number4
DOIs
Publication statusPublished - 2022

Keywords

  • Point Clouds
  • Point Cloud Classification
  • Point Cloud Segmentation
  • Point Cloud Learning
  • Point Cloud Processing
  • geometric deep learning
  • Graph CNN

Fingerprint

Dive into the research topics of 'DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds'. Together they form a unique fingerprint.

Cite this