Hierarchical Feature Fusion and Multi-scale Cost Aggregation for Stereo Matching

Jiaquan Zhang, Pengfei Li, Xin'an Wang, Yong Zhao
{"title":"Hierarchical Feature Fusion and Multi-scale Cost Aggregation for Stereo Matching","authors":"Jiaquan Zhang, Pengfei Li, Xin'an Wang, Yong Zhao","doi":"10.1109/CCET55412.2022.9906319","DOIUrl":null,"url":null,"abstract":"To further improve the accuracy of disparity estimation in ill-posed regions and weak texture regions, in this paper we propose HFMANet: which is a stereo matching method based on hierarchical feature fusion and multi-scale cost aggregation. Specifically, we first propose a hierarchical feature fusion module, which innovatively fuses low-level features and high-level features to obtain rich semantic information while retaining the edge information of the image. Secondly, we propose a multi-scale cost aggregation module to extract rich global context information. At the same time, the layer-by-layer fusion optimization helps increase the receptive field to capture more structural information, reduce the dependence on local information, and help the disparity estimation of ill-posed regions and weak-textured regions. Comprehensive experiments are conducted on the SceneFlow and KITTI datasets, and achieve competitive results, which proves the effectiveness of the proposed method.","PeriodicalId":329327,"journal":{"name":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 5th International Conference on Computer and Communication Engineering Technology (CCET)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCET55412.2022.9906319","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

To further improve the accuracy of disparity estimation in ill-posed regions and weak texture regions, in this paper we propose HFMANet: which is a stereo matching method based on hierarchical feature fusion and multi-scale cost aggregation. Specifically, we first propose a hierarchical feature fusion module, which innovatively fuses low-level features and high-level features to obtain rich semantic information while retaining the edge information of the image. Secondly, we propose a multi-scale cost aggregation module to extract rich global context information. At the same time, the layer-by-layer fusion optimization helps increase the receptive field to capture more structural information, reduce the dependence on local information, and help the disparity estimation of ill-posed regions and weak-textured regions. Comprehensive experiments are conducted on the SceneFlow and KITTI datasets, and achieve competitive results, which proves the effectiveness of the proposed method.
层次特征融合与多尺度代价聚合立体匹配
为了进一步提高病态区域和弱纹理区域视差估计的精度,本文提出了一种基于层次特征融合和多尺度代价聚合的立体匹配方法HFMANet。具体而言,我们首先提出了一种分层特征融合模块,该模块创新性地融合了低级特征和高级特征,在保留图像边缘信息的同时获得丰富的语义信息。其次,我们提出了一个多尺度成本聚合模块来提取丰富的全局上下文信息。同时,通过逐层融合优化,增加接收野以捕获更多的结构信息,减少对局部信息的依赖,有助于病态区域和弱纹理区域的视差估计。在SceneFlow和KITTI数据集上进行了综合实验,取得了比较好的结果,证明了所提方法的有效性。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信