High-dimensional Convolutional Networks for Geometric Pattern Recognition

2020/05/17 by Choy, Christopher, Lee, Junha, Ranftl, Rene +2 · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2005.08144

Abstract

Many problems in science and engineering can be formulated in terms of geometric patterns in high-dimensional spaces. We present high-dimensional convolutional networks (ConvNets) for pattern recognition problems that arise in the context of geometric registration. We first study the effectiveness of convolutional networks in detecting linear subspaces in high-dimensional spaces with up to 32 dimensions: much higher dimensionality than prior applications of ConvNets. We then apply high-dimensional ConvNets to 3D registration under rigid motions and image correspondence estimation. Experiments indicate that our high-dimensional ConvNets outperform prior approaches that relied on deep networks based on global pooling operators.

Cited by

• PointCNN++: Performant Convolution on Native Points

Related

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Convolutional neural network architecture for geometric matching
• Understanding deep convolutional networks
• Is Second-order Information Helpful for Large-scale Visual Recognition?
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges