4.7 Article

Learning Two-View Correspondences and Geometry Using Neighbor-Aware Network

Journal

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2022.3159571

Keywords

Correspondences; neighbor context; outlier removal; pose estimation

Funding

  1. National Natural Science Foundation of China [62072223]
  2. Natural Science Foundation of Fujian Province [2020J01131199]

Ask authors/readers for more resources

Finding reliable correspondences between two images is crucial in remote-sensing image registration. We propose a simple yet effective method to collect abundant local information by establishing a local neighborhood structure, extracting and aggregating neighborhood context, and thereby improving the registration performance.
Finding reliable correspondences between two images is a fundamental problem in remote-sensing image registration. In the face of sparse and unordered correspondences, the previous learning-based works often focus on global information and ignore valuable local information. To gather rich local information, we propose a simple and effective approach, the principle of which is to establish a local neighborhood structure for putative correspondences and then extract and aggregate neighborhood context. Specifically, we design a residual block with an innovative normalization operation and then we construct a sub-net, by introducing a competition mechanism in the local neighborhood to enhance the expression ability of features. Finally, we propose a learning-based network, to improve the performance of outlier rejection by extracting neighborhood context and global context. Extensive experiments on relative pose estimation demonstrate that the proposed network surpasses current state-of-the-art approaches on both challenging indoor and outdoor datasets.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available