MSA-Net: Establishing Reliable Correspondences by Multiscale Attention Network
- 1 July 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 4598-4608
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (62072223)
- Natural Science Foundation of Fujian Province (2020J01829)
This publication has 31 references indexed in Scilit:
- Feature Pyramid Networks for Object Detection2017
- Deep Residual Learning for Image Recognition2016
- ORB-SLAM: A Versatile and Accurate Monocular SLAM SystemIEEE Transactions on Robotics, 2015
- EVSAC: Accelerating Hypotheses Generation by Modeling Matching Scores with Extreme Value Theory2013
- Automatic Homographic Registration of a Pair of Images, with A Contrario Elimination of OutliersImage Processing On Line, 2012
- Modeling the World from Internet Photo CollectionsInternational Journal of Computer Vision, 2007
- Automatic Panoramic Image Stitching using Invariant FeaturesInternational Journal of Computer Vision, 2006
- Matching with PROSAC — Progressive Sample Consensus2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Random sample consensusCommunications of the ACM, 1981