Two-stage Parallax Correction and Multi-stage Cross-view Fusion Network Based Stereo Image Super-Resolution

Yijian Zheng, Sumei Li
{"title":"Two-stage Parallax Correction and Multi-stage Cross-view Fusion Network Based Stereo Image Super-Resolution","authors":"Yijian Zheng, Sumei Li","doi":"10.1109/VCIP53242.2021.9675418","DOIUrl":null,"url":null,"abstract":"Stereo image super-resolution (SR) has achieved great progress in recent years. However, the two major problems of the existing methods are that the parallax correction is insufficient and the cross-view information fusion only occurs in the beginning of the network. To address these problems, we propose a two-stage parallax correction and a multi-stage cross-view fusion network for better stereo image SR results. Specially, the two-stage parallax correction module consists of horizontal parallax correction and refined parallax correction. The first stage corrects horizontal parallax by parallax attention. The second stage is based on deformable convolution to refine horizontal parallax and correct vertical parallax simultaneously. Then, multiple cascaded enhanced residual spatial feature transform blocks are developed to fuse cross-view information at multiple stages. Extensive experiments show that our method achieves state-of-the-art performance on the KITTI2012, KITTI2015, Middlebury and Flickr1024 datasets.","PeriodicalId":114062,"journal":{"name":"2021 International Conference on Visual Communications and Image Processing (VCIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Visual Communications and Image Processing (VCIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/VCIP53242.2021.9675418","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

Stereo image super-resolution (SR) has achieved great progress in recent years. However, the two major problems of the existing methods are that the parallax correction is insufficient and the cross-view information fusion only occurs in the beginning of the network. To address these problems, we propose a two-stage parallax correction and a multi-stage cross-view fusion network for better stereo image SR results. Specially, the two-stage parallax correction module consists of horizontal parallax correction and refined parallax correction. The first stage corrects horizontal parallax by parallax attention. The second stage is based on deformable convolution to refine horizontal parallax and correct vertical parallax simultaneously. Then, multiple cascaded enhanced residual spatial feature transform blocks are developed to fuse cross-view information at multiple stages. Extensive experiments show that our method achieves state-of-the-art performance on the KITTI2012, KITTI2015, Middlebury and Flickr1024 datasets.
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
基于两级视差校正和多级交叉视点融合网络的立体图像超分辨率
立体图像超分辨率(SR)技术近年来取得了很大的进展。然而,现有方法存在视差校正不足和交叉视点信息融合只发生在网络初始阶段这两个主要问题。为了解决这些问题,我们提出了一种两阶段视差校正和多阶段交叉视点融合网络,以获得更好的立体图像SR结果。其中,两级视差校正模块包括水平视差校正和精细视差校正。第一阶段通过视差注意纠正水平视差。第二阶段是基于可变形卷积的水平视差细化和垂直视差校正同步进行。然后,开发多个级联的增强残差空间特征变换块,融合多阶段的交叉视图信息;大量的实验表明,我们的方法在KITTI2012, KITTI2015, Middlebury和Flickr1024数据集上达到了最先进的性能。
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
Seq-Masks: Bridging the gap between appearance and gait modeling for video-based person re-identification Deep Metric Learning for Human Action Recognition with SlowFast Networks LRS-Net: invisible QR Code embedding, detection, and restoration Deep Color Constancy Using Spatio-Temporal Correlation of High-Speed Video Large-Scale Crowdsourcing Subjective Quality Evaluation of Learning-Based Image Coding
×
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