Learning Two-View Correspondences and Geometry via Local Neighborhood Correlation

Learning Two-View Correspondences and Geometry via Local Neighborhood Correlation

Seeking quality feature correspondences (also known as matches) is a foundational step in computer vision. In our work, a novel and effective network with a stable local constraint, named the Local Neighborhood Correlation Network (LNCNet), is proposed to capture abundant contextual information of e...

Full description

Bibliographic Details
Main Authors: Luanyuan Dai, Xin Liu, Jingtao Wang, Changcai Yang, Riqing Chen
Format: Article
Language:English
Published: MDPI AG 2021-08-01
Series:Entropy
Subjects:
feature matching
outlier removal
pose estimation
neighborhood correlation
correspondence
Online Access:https://www.mdpi.com/1099-4300/23/8/1024

Internet

https://www.mdpi.com/1099-4300/23/8/1024

Similar Items