EUVIMEDEUVIMED entdecken
Crossref

T-Net++: Effective Permutation-Equivariance Network for Two-View Correspondence Pruning

Guobao Xiao, Xin Liu, Zhen Zhong, Xiaoqin Zhang, Jiayi Ma, Haibin Ling

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 10629-10644

DOI: 10.1109/tpami.2024.3444457 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Guobao Xiao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Zhejiang Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a conceptually novel, flexible, and effective framework (named T-Net++) for the task of two-view correspondence pruning. T-Net++ comprises two unique structures: the "-'' structure and the "|'' structure. The "-'' structure utilizes an iterative learning strategy to process correspondences, while the "|'' structure integrates all feature information of the "-'' structure and produces inlier weights. Moreover, within the "|'' structure, we design a new Local-Global Attention Fusion module to fully exploit valuable information obtained from concatenating features through channel-wise and spatial-wise relationships. Furthermore, we develop a Channel-Spatial Squeeze-and-Excitation module, a modified network backbone that enhances the representation ability of important channels and correspondences through the squeeze-and-excitation operation. T-Net++ not only preserves the permutation-equivariance manner for correspondence pruning, but also gathers rich contextual information, thereby enhancing the effectiveness of the network. Experimental results demonstrate that T-Net++ outperforms other state-of-the-art correspondence pruning methods on various benchmarks and excels in two extended tasks.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Zhejiang Province

Zitieren

APA

Xiao, G., Liu, X., Zhong, Z., Zhang, X., Ma, J., & Ling, H. (2024). T-Net++: Effective Permutation-Equivariance Network for Two-View Correspondence Pruning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 10629-10644. https://doi.org/10.1109/tpami.2024.3444457

Vancouver

Xiao G, Liu X, Zhong Z, Zhang X, Ma J, Ling H. T-Net++: Effective Permutation-Equivariance Network for Two-View Correspondence Pruning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):10629-10644. doi:10.1109/tpami.2024.3444457

BibTeX
@article{Xiao2024,
  author = {Xiao, Guobao and Liu, Xin and Zhong, Zhen and Zhang, Xiaoqin and Ma, Jiayi and Ling, Haibin},
  title = {T-Net++: Effective Permutation-Equivariance Network for Two-View Correspondence Pruning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {10629--10644},
  doi = {10.1109/tpami.2024.3444457}
}
Kostenlos starten →