High-dimensional Convolutional Networks for Geometric Pattern Recognition

Autor:	Choy, Christopher, Lee, Junha, Ranftl, Rene, Park, Jaesik, Koltun, Vladlen
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted for CVPR 2020 oral presentation
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2005.08144 Zobrazit plný text záznamu View this record from Arxiv