Outlier robust feature correspondence by learning based matching process

DOI10.1007/S11424-024-3141-0zbMATH Open1546.68029MaRDI QIDQ6595032FDOQ6595032

Authors: Xu Yang, Shaofeng Zeng, Zhi-Yong Liu 

Publication date: 29 August 2024

Published in: Journal of Systems Science and Complexity (Search for Journal in Brave)

Recommendations

• scientific article; zbMATH DE number 1945240
• ROML: a robust feature correspondence approach for matching objects in a set of images
• Robust homography estimation based on nonlinear least squares optimization
• scientific article; zbMATH DE number 1975572
• D3Former: jointly learning repeatable dense detectors and feature-enhanced descriptors via saliency-guided transformer

zbMATH Keywords

optimal transport problemfeature correspondencegraph neural networkpointmatching

Mathematics Subject Classification ID

Optimal transportation (49Q22) Artificial neural networks and deep learning (68T07) Variational problems in a geometric measure-theoretic setting (49Q20) Duality theory (optimization) (49N15) Machine vision and scene understanding (68T45)

Cites Work

• Concerning nonnegative matrices and doubly stochastic matrices
• Computational optimal transport. With applications to data sciences
• Title not available (Why is that?)
• Unsupervised learning for graph matching
• Machine learning for combinatorial optimization: a methodological tour d'horizon

This page was built for publication: Outlier robust feature correspondence by learning based matching process

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6595032)