NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences

Chen Zhao, Zhiguo Cao, Chi Li, Xin Li, Jiaqi Yang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 215-224

Abstract


Feature correspondence selection is pivotal to many feature-matching based tasks in computer vision. Searching spatially k-nearest neighbors is a common strategy for extracting local information in many previous works. However, there is no guarantee that the spatially k-nearest neighbors of correspondences are consistent because the spatial distribution of false correspondences is often irregular. To address this issue, we present a compatibility-specific mining method to search for consistent neighbors. Moreover, in order to extract and aggregate more reliable features from neighbors, we propose a hierarchical network named NM-Net with a series of graph convolutions that is insensitive to the order of correspondences. Our experimental results have shown the proposed method achieves the state-of-the-art performance on four datasets with various inlier ratios and varying numbers of feature consistencies.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhao_2019_CVPR,
author = {Zhao, Chen and Cao, Zhiguo and Li, Chi and Li, Xin and Yang, Jiaqi},
title = {NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}