Feature Matching via Topology-Aware Graph Interaction Model

计算机科学 离群值 成对比较 匹配(统计) 图形 算法 理论计算机科学 拓扑(电路) 特征(语言学) 模式识别(心理学) 人工智能 数据挖掘 数学 语言学 统计 哲学 组合数学
作者
Yifan Lu,Jiayi Ma,Xiaoguang Mei,Jun Huang,Xiao-Ping Zhang
出处
期刊:IEEE/CAA Journal of Automatica Sinica [Institute of Electrical and Electronics Engineers]
卷期号:11 (1): 113-130
标识
DOI:10.1109/jas.2023.123774
摘要

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 formulation can be solved globally by graph cut algorithm. Our new formulation 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 feature 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 publicly available at http://github.com/YifanLu2000/TIM.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
刚刚
FashionBoy应助内向寒云采纳,获得30
1秒前
wrzzz发布了新的文献求助10
1秒前
1秒前
2秒前
活泼的飞扬完成签到,获得积分10
2秒前
ccc完成签到,获得积分10
2秒前
mo发布了新的文献求助10
2秒前
3秒前
4秒前
且陶陶发布了新的文献求助10
4秒前
wbh发布了新的文献求助10
4秒前
诗意Sy发布了新的文献求助10
4秒前
4秒前
4秒前
5秒前
可爱的函函应助和和采纳,获得10
6秒前
6秒前
无奈镜子发布了新的文献求助10
6秒前
李瑞卿完成签到 ,获得积分10
7秒前
Young发布了新的文献求助10
7秒前
xiaowu发布了新的文献求助10
7秒前
英俊的铭应助zwhy采纳,获得10
7秒前
CipherSage应助傻傻的芷巧采纳,获得10
8秒前
8秒前
小梁发布了新的文献求助10
8秒前
8秒前
gaterina发布了新的文献求助10
9秒前
自信的秋灵完成签到,获得积分10
9秒前
9秒前
小白发布了新的文献求助10
10秒前
充电宝应助Juvenilesy采纳,获得30
10秒前
西西发布了新的文献求助10
11秒前
momo发布了新的文献求助10
11秒前
xiaowu完成签到,获得积分10
11秒前
11秒前
11秒前
12秒前
12秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3971125
求助须知:如何正确求助?哪些是违规求助? 3515824
关于积分的说明 11179811
捐赠科研通 3250971
什么是DOI,文献DOI怎么找? 1795610
邀请新用户注册赠送积分活动 875897
科研通“疑难数据库(出版商)”最低求助积分说明 805207