PESA-Net: Permutation-Equivariant Split Attention Network for correspondence learning
| Autor: | Zhen Zhong, Guobao Xiao, Xiaoqin Zhang, Shiping Wang, Leyi Wei |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Source code
Artificial neural network Computer science business.industry media_common.quotation_subject Pattern recognition Context (language use) Perceptron Hardware and Architecture Essential matrix Signal Processing Outlier Artificial intelligence business Pose Software Information Systems media_common Block (data storage) |
| Zdroj: | Information Fusion. 77:81-89 |
| ISSN: | 1566-2535 |
| DOI: | 10.1016/j.inffus.2021.07.018 |
| Popis: | 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 . |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect