Feature Point Matching in Cross-Spectral Images with Cycle Consistency Learning
Feature Point Matching in Cross-Spectral Images with Cycle Consistency Learning
复制标题
DOI：
10.1109/icpr48806.2021.9412977
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Ryosuke Furuta;Naoaki Noguchi;Xueting Wang;T. Yamasaki
中科院分区：
文献类型：
--
作者：
Ryosuke Furuta;Naoaki Noguchi;Xueting Wang;T. Yamasaki
特征点匹配是计算机视觉中的一个重要问题，因为它的应用范围很广。基于深度学习的局部特征学习方法最近表现出了上级性能。然而，这是不容易收集的训练数据在这些方法中，特别是在交叉光谱设置，如RGB和近红外图像之间的对应关系。在本文中，我们提出了一种无监督学习方法的一般特征点匹配。因为我们训练卷积神经网络作为特征提取器，以满足输入图像对之间的对应关系的周期一致性，所以所提出的方法不需要监督，即使在交叉谱设置中也可以工作。在我们的实验中，我们将所提出的方法应用到立体匹配，这是一个密集的特征点匹配问题。实验结果，模拟交叉光谱设置与三个不同的设置，即，RGB立体，RGB与灰度，和anaglUNK（红色与青色），表明我们提出的方法优于比较的方法，采用手工制作的立体匹配功能，由一个显着的利润率。
Feature point matching is an important problem because its applications cover a wide range of tasks in computer vision. Deep learning-based methods for learning local features have recently shown superior performance. However, it is not easy to collect the training data in these methods, especially in cross-spectral settings such as the correspondence between RGB and near-infrared images. In this paper, we propose an unsupervised learning method for general feature point matching. Because we train a convolutional neural network as a feature extractor in order to satisfy the cycle consistency of the correspondences between an input image pair, the proposed method does not require supervision and works even in cross-spectral settings. In our experiments, we apply the proposed method to stereo matching, which is a dense feature point matching problem. The experimental results, which simulate cross-spectral settings with three different settings, i.e., RGB stereo, RGB vs gray-scale, and anaglyph (red vs cyan), show that our proposed method outperforms the compared methods, which employ handcrafted features for stereo matching, by a significant margin.