NM-Net: Mining reliable neighbors for robust feature correspondences

C Zhao, Z Cao, C Li, X Li… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
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 …

Learning second-order attentive context for efficient correspondence pruning

X Ye, W Zhao, H Lu, Z Cao - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Correspondence pruning aims to search consistent correspondences (inliers) from a set of
putative correspondences. It is challenging because of the disorganized spatial distribution …

CE-Net: A coordinate embedding network for mismatching removal

S Chen, J Niu, C Deng, Y Zhang, F Chen, F Xu - IEEE Access, 2021 - ieeexplore.ieee.org
Mismatching removal is at the core yet still a challenging problem in the photogrammetry
and computer vision field. In this paper, we propose a coordinate embedding network …

Iterative Clustering with Game-Theoretic Matching for Robust Multi-consistency Correspondence

C Zhao, J Yang, K **an, Z Cao, X Li - arxiv preprint arxiv:1909.01497, 2019 - arxiv.org
Matching corresponding features between two images is a fundamental task to computer
vision with numerous applications in object recognition, robotics, and 3D reconstruction …