TMSF: Taylor expansion approximation network with multi-stage feature representation for optical flow estimation

IF 2.9 3区 工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC
Zhenghua Huang , Wen Hu , Zifan Zhu , Qian Li , Hao Fang
{"title":"TMSF: Taylor expansion approximation network with multi-stage feature representation for optical flow estimation","authors":"Zhenghua Huang ,&nbsp;Wen Hu ,&nbsp;Zifan Zhu ,&nbsp;Qian Li ,&nbsp;Hao Fang","doi":"10.1016/j.dsp.2025.105157","DOIUrl":null,"url":null,"abstract":"<div><div>Optical flow estimation is a fundamental task in computer vision. Existing CNN-based and transformer-based methods have proven their powerful ability in generating preferable performance, but they still suffer from the loss of fine details and objects' shape. To cope with these problems, this paper develops a Taylor expansion approximation network with multi-stage feature representation, namely TMSF, including a basic network and a refine network. In the basic network, multi-stage modules, including feature enhancement module (FEM) for enriching image features, feature/context network for feature extraction, and iterative update module (IUM) for coarse optical flow estimation, are employed to represent fine features. In the refine network, a refinement architecture is constructed based on the third-order Taylor approximation expansion to further refine features from the basic network for optical flow, in which a feature attention module (FAM) is used to estimate each derivative layer. Meanwhile, a novel loss function is formed by end-point-error (EPE) and structural similarity (SSIM) to ensure the convergence of our TMSF to a satisfactory solution. Quantitative associated with qualitative experimental results validate that our TMSF performs better than state-of-the-art optical flow estimation methods on performance improvement and shape preservation. The code will be available at <span><span>https://github.com/MysterYxby/TMSF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"162 ","pages":"Article 105157"},"PeriodicalIF":2.9000,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Digital Signal Processing","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1051200425001794","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Optical flow estimation is a fundamental task in computer vision. Existing CNN-based and transformer-based methods have proven their powerful ability in generating preferable performance, but they still suffer from the loss of fine details and objects' shape. To cope with these problems, this paper develops a Taylor expansion approximation network with multi-stage feature representation, namely TMSF, including a basic network and a refine network. In the basic network, multi-stage modules, including feature enhancement module (FEM) for enriching image features, feature/context network for feature extraction, and iterative update module (IUM) for coarse optical flow estimation, are employed to represent fine features. In the refine network, a refinement architecture is constructed based on the third-order Taylor approximation expansion to further refine features from the basic network for optical flow, in which a feature attention module (FAM) is used to estimate each derivative layer. Meanwhile, a novel loss function is formed by end-point-error (EPE) and structural similarity (SSIM) to ensure the convergence of our TMSF to a satisfactory solution. Quantitative associated with qualitative experimental results validate that our TMSF performs better than state-of-the-art optical flow estimation methods on performance improvement and shape preservation. The code will be available at https://github.com/MysterYxby/TMSF.
基于多阶段特征表示的Taylor展开近似网络光流估计
光流估计是计算机视觉中的一项基本任务。现有的基于cnn和基于变压器的方法已经证明了它们产生良好性能的强大能力,但它们仍然存在精细细节和物体形状丢失的问题。为了解决这些问题,本文提出了一种多阶段特征表示的Taylor展开近似网络,即TMSF,包括一个基本网络和一个细化网络。在基础网络中,采用多阶段模块,包括用于丰富图像特征的特征增强模块(FEM)、用于特征提取的特征/上下文网络(feature/context network)和用于粗光流估计的迭代更新模块(IUM)来表示精细特征。在细化网络中,基于三阶泰勒近似展开构建了一种细化体系,从光流基本网络中进一步细化特征,其中使用特征关注模块(FAM)对每个导数层进行估计。同时,利用端点误差(EPE)和结构相似度(SSIM)构造了一种新的损失函数,以保证TMSF收敛到满意的解。定量和定性实验结果验证了我们的TMSF在性能改进和形状保持方面优于最先进的光流估计方法。代码可在https://github.com/MysterYxby/TMSF上获得。
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
Digital Signal Processing
Digital Signal Processing 工程技术-工程:电子与电气
CiteScore
5.30
自引率
17.20%
发文量
435
审稿时长
66 days
期刊介绍: Digital Signal Processing: A Review Journal is one of the oldest and most established journals in the field of signal processing yet it aims to be the most innovative. The Journal invites top quality research articles at the frontiers of research in all aspects of signal processing. Our objective is to provide a platform for the publication of ground-breaking research in signal processing with both academic and industrial appeal. The journal has a special emphasis on statistical signal processing methodology such as Bayesian signal processing, and encourages articles on emerging applications of signal processing such as: • big data• machine learning• internet of things• information security• systems biology and computational biology,• financial time series analysis,• autonomous vehicles,• quantum computing,• neuromorphic engineering,• human-computer interaction and intelligent user interfaces,• environmental signal processing,• geophysical signal processing including seismic signal processing,• chemioinformatics and bioinformatics,• audio, visual and performance arts,• disaster management and prevention,• renewable energy,
×
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