DHM-Net: Deep Hypergraph Modeling for Robust Feature Matching

超图 计算机科学 人工智能 模式识别(心理学) 匹配(统计) 特征(语言学) 稳健性(进化) 特征提取 算法 数学 统计 哲学 离散数学 基因 化学 生物化学 语言学
作者
Shunxing Chen,Guobao Xiao,Junwen Guo,Qiangqiang Wu,Jiayi Ma
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:: 1-1
标识
DOI:10.1109/tip.2024.3477916
摘要

We present a novel deep hypergraph modeling architecture (called DHM-Net) for feature matching in this paper. Our network focuses on learning reliable correspondences between two sets of initial feature points by establishing a dynamic hypergraph structure that models group-wise relationships and assigns weights to each node. Compared to existing feature matching methods that only consider pair-wise relationships via a simple graph, our dynamic hypergraph is capable of modeling nonlinear higher-order group-wise relationships among correspondences in an interaction capturing and attention representation learning fashion. Specifically, we propose a novel Deep Hypergraph Modeling block, which initializes an overall hypergraph by utilizing neighbor information, and then adopts node-to-hyperedge and hyperedge-to-node strategies to propagate interaction information among correspondences while assigning weights based on hypergraph attention. In addition, we propose a Differentiation Correspondence-Aware Attention mechanism to optimize the hypergraph for promoting representation learning. The proposed mechanism is able to effectively locate the exact position of the object of importance via the correspondence aware encoding and simple feature gating mechanism to distinguish candidates of inliers. In short, we learn such a dynamic hypergraph format that embeds deep group-wise interactions to explicitly infer categories of correspondences. To demonstrate the effectiveness of DHM-Net, we perform extensive experiments on both real-world outdoor and indoor datasets. Particularly, experimental results show that DHM-Net surpasses the state-of-the-art method by a sizable margin. Our approach obtains an 11.65% improvement under error threshold of 5° for relative pose estimation task on YFCC100M dataset. Code will be released at https://github.com/CSX777/DHM-Net.
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
汉堡包应助666采纳,获得10
刚刚
Hello应助贰叁采纳,获得10
刚刚
上官若男应助hugdoggy采纳,获得10
2秒前
emmm完成签到,获得积分10
2秒前
斯文败类应助anna采纳,获得10
3秒前
4秒前
默默的惜灵完成签到 ,获得积分10
4秒前
22发布了新的文献求助10
4秒前
Lucas应助pomfret采纳,获得10
6秒前
7秒前
7秒前
科目三应助娇气的天亦采纳,获得10
8秒前
JiangHan发布了新的文献求助10
8秒前
10秒前
GGBOND发布了新的文献求助10
10秒前
11秒前
黄振全发布了新的文献求助10
11秒前
12秒前
Lu发布了新的文献求助10
13秒前
苯氮小羊发布了新的文献求助10
13秒前
hugdoggy发布了新的文献求助10
15秒前
15秒前
英姑应助shawn采纳,获得10
18秒前
完美世界应助22采纳,获得10
18秒前
Hululu完成签到,获得积分10
18秒前
19秒前
精美礼物发布了新的文献求助30
20秒前
anna发布了新的文献求助10
20秒前
GGBOND发布了新的文献求助10
25秒前
pomfret完成签到,获得积分10
25秒前
从容甜瓜完成签到 ,获得积分10
27秒前
量子星尘发布了新的文献求助10
27秒前
28秒前
29秒前
桐桐应助Lu采纳,获得10
30秒前
YWang发布了新的文献求助10
32秒前
han应助归华采纳,获得10
33秒前
33秒前
SYLH应助zly采纳,获得30
36秒前
完美世界应助娇气的天亦采纳,获得10
38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
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3989115
求助须知:如何正确求助?哪些是违规求助? 3531367
关于积分的说明 11253688
捐赠科研通 3269986
什么是DOI,文献DOI怎么找? 1804868
邀请新用户注册赠送积分活动 882078
科研通“疑难数据库(出版商)”最低求助积分说明 809105