Matching Images from Different Viewpoints with Deep Learning Based on LoFTR and MAGSAC++

Liang Tian
{"title":"Matching Images from Different Viewpoints with Deep Learning Based on LoFTR and MAGSAC++","authors":"Liang Tian","doi":"10.1145/3582177.3582181","DOIUrl":null,"url":null,"abstract":"Matching 2D images from different viewpoints plays a crucial role in the fields of Structure-from-Motion and 3D reconstruction. However, image matching for assorted and unstructured images with a wide variety of viewpoints leads to difficulty for traditional matching methods. In this paper, we propose a Transformer-based feature matching approach to capture the same physical points of a scene from two images with different viewpoints. The local features of images are extracted by the LoFTR, which is a detector-free deep-learning matching model on the basis of Transformer. The subsequent matching process is realized by the MAGSAC++ estimator, where the matching results are summarized in the fundamental matrix as the model output. By removing image feature points with low confidence scores and applying the test time augmentation, our approach can reach a mean Average Accuracy 0.81340 in the Kaggle competition Image Matching Challenge 2022. This score ranks 45/642 in the competition leaderboard, and can get a silver medal in this competition. Our work could help accelerate the research of generalized methods for Structure-from-Motion and 3D reconstruction, and would potentially deepen the understanding of image feature matching and related fields.","PeriodicalId":170327,"journal":{"name":"Proceedings of the 2023 5th International Conference on Image Processing and Machine Vision","volume":"58 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2023 5th International Conference on Image Processing and Machine Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3582177.3582181","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Matching 2D images from different viewpoints plays a crucial role in the fields of Structure-from-Motion and 3D reconstruction. However, image matching for assorted and unstructured images with a wide variety of viewpoints leads to difficulty for traditional matching methods. In this paper, we propose a Transformer-based feature matching approach to capture the same physical points of a scene from two images with different viewpoints. The local features of images are extracted by the LoFTR, which is a detector-free deep-learning matching model on the basis of Transformer. The subsequent matching process is realized by the MAGSAC++ estimator, where the matching results are summarized in the fundamental matrix as the model output. By removing image feature points with low confidence scores and applying the test time augmentation, our approach can reach a mean Average Accuracy 0.81340 in the Kaggle competition Image Matching Challenge 2022. This score ranks 45/642 in the competition leaderboard, and can get a silver medal in this competition. Our work could help accelerate the research of generalized methods for Structure-from-Motion and 3D reconstruction, and would potentially deepen the understanding of image feature matching and related fields.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于LoFTR和MAGSAC++的深度学习不同视点图像匹配
不同视点的二维图像匹配在运动生成结构和三维重建中起着至关重要的作用。然而,对于视点繁多的非结构化、杂类图像的匹配,给传统匹配方法带来了困难。在本文中,我们提出了一种基于transformer的特征匹配方法,以从不同视点的两幅图像中捕获场景的相同物理点。LoFTR是一种基于Transformer的无检测器深度学习匹配模型,它提取图像的局部特征。后续匹配过程由MAGSAC++估计器实现,匹配结果汇总到基本矩阵中作为模型输出。通过去除置信度较低的图像特征点并应用测试时间增强,我们的方法在Kaggle image Matching Challenge 2022中平均准确率达到0.81340。这个分数在比赛排行榜上排名45/642,可以在本次比赛中获得银牌。我们的工作有助于加速广义的运动生成结构和三维重建方法的研究,并有可能加深对图像特征匹配和相关领域的理解。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
VVC Coding Unit Partitioning Decision based on Naive Bayes Theory Human Motion Prediction based on IMUs and MetaFormer Semi-supervised Defect Segmentation with Uncertainty-aware Pseudo-labels from Multi-branch Network A Fast CU Partitioning Algorithm Based on Texture Characteristics for VVC Attention Based BiGRU-2DCNN with Hunger Game Search Technique for Low-Resource Document-Level Sentiment Classification
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1