diffConv: Analyzing Irregular Point Clouds with an Irregular View

29 Nov 2021  ·  Manxi Lin, Aasa Feragen ·

Standard spatial convolutions assume input data with a regular neighborhood structure. Existing methods typically generalize convolution to the irregular point cloud domain by fixing a regular "view" through e.g. a fixed neighborhood size, where the convolution kernel size remains the same for each point. However, since point clouds are not as structured as images, the fixed neighbor number gives an unfortunate inductive bias. We present a novel graph convolution named Difference Graph Convolution (diffConv), which does not rely on a regular view. diffConv operates on spatially-varying and density-dilated neighborhoods, which are further adapted by a learned masked attention mechanism. Experiments show that our model is very robust to the noise, obtaining state-of-the-art performance in 3D shape classification and scene understanding tasks, along with a faster inference speed.

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods