Back to Search
Start Over
PESA-Net: Permutation-Equivariant Split Attention Network for correspondence learning.
- Source :
-
Information Fusion . Jan2022, Vol. 77, p81-89. 9p. - Publication Year :
- 2022
-
Abstract
- Establishing reliable correspondences by a deep neural network is an important task in computer vision, and it generally requires permutation-equivariant architecture and rich contextual information. In this paper, we design a Permutation-Equivariant Split Attention Network (called PESA-Net), to gather rich contextual information for the feature matching task. Specifically, we propose a novel "Split–Squeeze–Excitation–Union" (SSEU) module. The SSEU module not only generates multiple paths to exploit the geometrical context of putative correspondences from different aspects, but also adaptively captures channel-wise global information by explicitly modeling the interdependencies between the channels of features. In addition, we further construct a block by fusing the SSEU module, Multi-Layer Perceptron and some normalizations. The proposed PESA-Net is able to effectively infer the probabilities of correspondences being inliers or outliers and simultaneously recover the relative pose by essential matrix. Experimental results demonstrate that the proposed PESA-Net relative surpasses state-of-the-art approaches for pose estimation and outlier rejection on both outdoor scenes and indoor scenes (i.e., YFCC100M and SUN3D). Source codes: https://github.com/x-gb/PESA-Net. • We propose an iterative network to establish reliable correspondences. • We develop an attention mechanism to capture rich contextual information. • We construct a novel block to exploit the global context of unordered data. • The proposed network achieves the state-of-the-art performance. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 15662535
- Volume :
- 77
- Database :
- Academic Search Index
- Journal :
- Information Fusion
- Publication Type :
- Academic Journal
- Accession number :
- 152368323
- Full Text :
- https://doi.org/10.1016/j.inffus.2021.07.018