MSA-Net: Establishing Reliable Correspondences by Multiscale Attention Network

In this paper, we propose a novel multi-scale attention based network (called MSA-Net) for feature matching problems. Current deep networks based feature matching methods suffer from limited effectiveness and robustness when applied to different scenarios, due to random distributions of outliers and...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2022-01, Vol.31, p.4598-4608
Main Authors: Zheng, Linxin, Xiao, Guobao, Shi, Ziwei, Wang, Shiping, Ma, Jiayi
Format: Article
Language:English
Subjects:
Context
Context modeling
Data mining
Datasets
Deep learning
Feature extraction
Feature maps
Inliers (landforms)
Matching
Outlier removal
Outliers (statistics)
Parameters
Pose estimation
Robustness
Task analysis
wide-baseline stereo
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a novel multi-scale attention based network (called MSA-Net) for feature matching problems. Current deep networks based feature matching methods suffer from limited effectiveness and robustness when applied to different scenarios, due to random distributions of outliers and insufficient information learning. To address this issue, we propose a multi-scale attention block to enhance the robustness to outliers, for improving the representational ability of the feature map. In addition, we also design a novel context channel refine block and a context spatial refine block to mine the information context with less parameters along channel and spatial dimensions, respectively. The proposed MSA-Net is able to effectively infer the probability of correspondences being inliers with less parameters. Extensive experiments on outlier removal and relative pose estimation have shown the performance improvements of our network over current state-of-the-art methods with less parameters on both outdoor and indoor datasets. Notably, our proposed network achieves an 11.7% improvement at error threshold 5° without RANSAC than the state-of-the-art method on relative pose estimation task when trained on YFCC100M dataset.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2022.3186535