U-Match: Exploring Hierarchy-Aware Local Context for Two-View Correspondence Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 10960-10977
DOI: 10.1109/tpami.2024.3447048 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Zizhuo Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Rejecting outlier correspondences is one of the critical steps for successful feature-based two-view geometry estimation, and contingent heavily upon local context exploration. Recent advances focus on devising elaborate local context extractors whereas typically adopting explicit neighborhood relationship modeling at a specific scale, which is intrinsically flawed and inflexible, because 1) severe outliers often populated in putative correspondences and 2) the uncertainty in the distribution of inliers and outliers make the network incapable of capturing adequate and reliable local context from such neighborhoods, therefore resulting in the failure of pose estimation. This prospective study proposes a novel network called U-Match that has the flexibility to enable implicit local context awareness at multiple levels, naturally circumventing the aforementioned issues that plague most existing studies. Specifically, to aggregate multi-level local context implicitly, a hierarchy-aware graph representation module is designed to flexibly encode and decode hierarchical features. Moreover, considering that global context always works collaboratively with local context, an orthogonal local-and-global information fusion module is presented to integrate complementary local and global context in a redundancy-free manner, thus yielding compact feature representations to facilitate correspondence learning. Thorough experimentation across relative pose estimation, homography estimation, visual localization, and point cloud registration affirms U-Match's remarkable capabilities.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Li, Z., Zhang, S., & Ma, J. (2024). U-Match: Exploring Hierarchy-Aware Local Context for Two-View Correspondence Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 10960-10977. https://doi.org/10.1109/tpami.2024.3447048
Vancouver
Li Z, Zhang S, Ma J. U-Match: Exploring Hierarchy-Aware Local Context for Two-View Correspondence Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):10960-10977. doi:10.1109/tpami.2024.3447048
BibTeX
@article{Li2024,
author = {Li, Zizhuo and Zhang, Shihua and Ma, Jiayi},
title = {U-Match: Exploring Hierarchy-Aware Local Context for Two-View Correspondence Learning},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {12},
pages = {10960--10977},
doi = {10.1109/tpami.2024.3447048}
}
EUVIMED