ResMatch: Residual Attention Learning for Feature Matching
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (2) · 1501-1509
DOI: 10.1609/aaai.v38i2.27915 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yuxin Deng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref).
Abstract (Originalsprache)
Attention-based graph neural networks have made great progress in feature matching. However, the literature lacks a comprehensive understanding of how the attention mechanism operates for feature matching. In this paper, we rethink cross- and self-attention from the viewpoint of traditional feature matching and filtering. To facilitate the learning of matching and filtering, we incorporate the similarity of descriptors into cross-attention and relative positions into self-attention. In this way, the attention can concentrate on learning residual matching and filtering functions with reference to the basic functions of measuring visual and spatial correlation. Moreover, we leverage descriptor similarity and relative positions to extract inter- and intra-neighbors. Then sparse attention for each point can be performed only within its neighborhoods to acquire higher computation efficiency. Extensive experiments, including feature matching, pose estimation and visual localization, confirm the superiority of the proposed method. Our codes are available at https://github.com/ACuOoOoO/ResMatch.
Zitieren
APA
Deng, Y., Zhang, K., Zhang, S., Li, Y., & Ma, J. (2024). ResMatch: Residual Attention Learning for Feature Matching. Proceedings of the AAAI Conference on Artificial Intelligence, 38(2), 1501-1509. https://doi.org/10.1609/aaai.v38i2.27915
Vancouver
Deng Y, Zhang K, Zhang S, Li Y, Ma J. ResMatch: Residual Attention Learning for Feature Matching. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(2):1501-1509. doi:10.1609/aaai.v38i2.27915
BibTeX
@article{Deng2024,
author = {Deng, Yuxin and Zhang, Kaining and Zhang, Shihua and Li, Yansheng and Ma, Jiayi},
title = {ResMatch: Residual Attention Learning for Feature Matching},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {2},
pages = {1501--1509},
doi = {10.1609/aaai.v38i2.27915}
}
EUVIMED