首页|Feature Matching via Topology-A ware Graph Interaction Model
Feature Matching via Topology-A ware Graph Interaction Model
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
国家科技期刊平台
NETL
NSTL
万方数据
Feature matching plays a key role in computer vision.However,due to the limitations of the descriptors,the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier filtering problem from two aspects.First,a robust and efficient graph interaction model,is proposed,with the assumption that matches are correlated with each other rather than independently distributed.To this end,we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem,where the pairwise term encodes the interaction between matches.We further show that this formula-tion can be solved globally by graph cut algorithm.Our new for-mulation always improves the performance of previous locality-based method without noticeable deterioration in processing time,adding a few milliseconds.Second,to construct a better graph structure,a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches.The two components in sum lead to topology interaction matching(TIM),an effective and efficient method for outlier filtering.Extensive experiments on several large and diverse datasets for multiple vision tasks including general fea-ture matching,as well as relative pose estimation,homography and fundamental matrix estimation,loop-closure detection,and multi-modal image matching,demonstrate that our TIM is more competitive than current state-of-the-art methods,in terms of generality,efficiency,and effectiveness.The source code is pub-licly available at http://github.com/YifanLu2000/TIM.
Electronic Information School,Wuhan University,Wuhan 430072,China
Tsinghua Berkeley Shenzhen Institute,Shenzhen 518071,China,and also with the Department of Electrical,Computer and Biomedical Engineering,Toronto Metropolitan University,Toronto ON M5B 2K3,Canada
国家科技期刊平台
NSTL
万方数据
