High-dimensional Convolutional Networks for Geometric Pattern Recognition

CVPR(2020)

引用 33|浏览321
暂无评分
摘要
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.
更多
查看译文
关键词
6-dimensional space,2D registration problems,computer vision problems,geometric pattern recognition problems,high-dimensional geometric patterns,4-dimensional hyper-conic section,high-dimensional linear regression problems,high-dimensional convolutional networks,3D registration problems
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要