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.
@article{arxiv.2005.08144,
title = {High-dimensional Convolutional Networks for Geometric Pattern Recognition},
author = {Christopher Choy and Junha Lee and Rene Ranftl and Jaesik Park and Vladlen Koltun},
journal= {arXiv preprint arXiv:2005.08144},
year = {2020}
}