计算机科学
卷积神经网络
图形
人工智能
一般化
模式识别(心理学)
匹配(统计)
卷积(计算机科学)
直线(几何图形)
特征(语言学)
特征匹配
算法
特征提取
人工神经网络
理论计算机科学
数学
数学分析
语言学
统计
哲学
几何学
作者
Quanmeng Ma,Guang Jiang,Jiajie Wu,Changshuai Cai,Dianzhi Lai,Zixuan Bai,Chen Hao
标识
DOI:10.1016/j.neucom.2021.04.125
摘要
Line matching plays an essential role in Structure from Motion (SFM) and Simultaneous Localization and Mapping (SLAM), especially in low-texture scenes, where feature points are hard to be detected. In this paper, we present a new method by combining Convolutional Neural Networks and Graph Convolutional Networks to match line segments in pairs of images. We design a graph-based method to predict the assignment matrix of two feature sets with solving a relaxed optimal transport problem. In contrast to handcrafted line matching algorithms, our approach learns the line segment features and performs matching simultaneously through end-to-end weakly supervised training. The experiment results show that our method outperforms the state-of-the-art techniques and is robust to various image transformations. Besides, the generalization experiment illustrates that our method has good generalization ability without fine-tuning. The code of our work is available at https://github.com/mameng1/GraphLineMatching.
科研通智能强力驱动
Strongly Powered by AbleSci AI