RoSe: Rotation-Invariant Sequence-Aware Consensus for Robust Correspondence Pruning
Open Access
- 28 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 7754-7763
Abstract
Correspondence pruning has recently drawn considerable attention as a crucial step in image matching. Existing methods typically achieve this by constructing neighborhoods for each feature point and imposing neighborhood consistency. However, the nearest-neighbor matching strategy often results in numerous many-to-one correspondences, thereby reducing the reliability of neighborhood information. Furthermore, the smoothness constraint fails in cases of large-scale rotations, leading to misjudgments. To address the above issues, this paper proposes a novel robust correspondence pruning method termed RoSe, which is based on rotation-invariant sequence-aware consensus. We formulate the correspondence pruning problem as a mathematical optimization problem and derive a closed-form solution. Specifically, we devise a rectified local neighborhood construction strategy that effectively enlarges the distribution between inliers and outliers. Meanwhile, to accommodate large-scale rotation, we propose a relative sequence-aware consistency as an alternative to existing smoothness constraints, which can better characterize the topological structure of inliers. Experimental results on image matching and registration tasks demonstrate the effectiveness of our method. Robustness analysis involving diverse feature descriptors and varying rotation degrees further showcases the efficacy of our method.Keywords
Funding Information
- Shanghai Municipal Science and Technology Major Project (2021SHZDZX0100)
- National Key R&D Program of China (2023YFC3806000 and 2023YFC3806002)
- National Natural Science Foundation of China (61936014)
- Shanghai Science and Technology Innovation Action Plan Project (22511105300)
This publication has 41 references indexed in Scilit:
- Multi-granularity Cross Transformer Network for person re-identificationPattern Recognition, 2024
- Feature Matching via Motion-Consistency Driven Probabilistic Graphical ModelInternational Journal of Computer Vision, 2022
- A review of multimodal image matching: Methods and applicationsInformation Fusion, 2021
- Image Matching from Handcrafted to Deep Features: A SurveyInternational Journal of Computer Vision, 2020
- GMS: Grid-Based Motion Statistics for Fast, Ultra-robust Feature CorrespondenceInternational Journal of Computer Vision, 2019
- NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences2019
- Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions2018
- 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions2017
- A Comparison of Affine Region DetectorsInternational Journal of Computer Vision, 2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004