View in EDS HTML Full Text PDF Full Text

Multi-view stereo algorithms based on deep learning: a survey.

Saved in:
Bibliographic Details
Title: Multi-view stereo algorithms based on deep learning: a survey.
Authors: Huang, Hongbo1,2 (AUTHOR) hhb@bistu.edu.cn, Yan, Xiaoxu1 (AUTHOR) 2021020568@bistu.edu.cn, Zheng, Yaolin1 (AUTHOR) 2021020574@bistu.edu.cn, He, Jiayu1 (AUTHOR) hejiayu_97@163.com, Xu, Longfei1 (AUTHOR) 2022020601@bistu.edu.cn, Qin, Dechun3 (AUTHOR) derekqin@126.com
Source: Multimedia Tools & Applications. Feb2025, Vol. 84 Issue 6, p2877-2908. 32p.
Subjects: Stereo image processing, Computer vision, Artificial intelligence, Depth maps (Digital image processing), Process capability, Deep learning
Abstract: Multi-View Stereo (MVS) is a long-standing and fundamental task in computer vision, which aims to reconstruct the 3D geometry of a scene from a set of overlapping images. With known camera parameters, MVS matches pixels across images to compute dense correspondences and recover 3D points. Traditional MVS methods often encounter difficulties in addressing complex scenes due to limitations in robustness. However, recent advancements in deep-learning-based MVS have demonstrated remarkable performance gains, attributed to their enhanced feature extraction and cost volume processing capabilities. This comprehensive survey delves into deep-learning-based MVS algorithms, highlighting key challenges and avenues for future exploration. Our focus is on studies aimed at mitigating algorithmic memory requirements and elevating processing speeds. To better understand the developments in this field, we propose a new taxonomy. The deep-learning-based MVS algorithms are categorized into two categories: scene-oriented and view-oriented methods. Scene-oriented methods typically employ voxels or neural implicit representations as the representative form of the scene and infer the complete scene directly. View-oriented methods focus on estimating the depth map of a single view. Detailed classifications and reviews have been conducted for each category. Furthermore, we introduce several widely used datasets and metrics and empirical evaluation of representative algorithms across three popular datasets. This article concludes by discussing prevalent challenges in the MVS domain and promising research directions for the future. [ABSTRACT FROM AUTHOR]
Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 182975009
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Multi-view stereo algorithms based on deep learning: a survey.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Huang%2C+Hongbo%22">Huang, Hongbo</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> hhb@bistu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Yan%2C+Xiaoxu%22">Yan, Xiaoxu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 2021020568@bistu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zheng%2C+Yaolin%22">Zheng, Yaolin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 2021020574@bistu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22He%2C+Jiayu%22">He, Jiayu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> hejiayu_97@163.com</i><br /><searchLink fieldCode="AR" term="%22Xu%2C+Longfei%22">Xu, Longfei</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 2022020601@bistu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Qin%2C+Dechun%22">Qin, Dechun</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> derekqin@126.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Multimedia+Tools+%26+Applications%22">Multimedia Tools & Applications</searchLink>. Feb2025, Vol. 84 Issue 6, p2877-2908. 32p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Stereo+image+processing%22">Stereo image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Depth+maps+%28Digital+image+processing%29%22">Depth maps (Digital image processing)</searchLink><br /><searchLink fieldCode="DE" term="%22Process+capability%22">Process capability</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Multi-View Stereo (MVS) is a long-standing and fundamental task in computer vision, which aims to reconstruct the 3D geometry of a scene from a set of overlapping images. With known camera parameters, MVS matches pixels across images to compute dense correspondences and recover 3D points. Traditional MVS methods often encounter difficulties in addressing complex scenes due to limitations in robustness. However, recent advancements in deep-learning-based MVS have demonstrated remarkable performance gains, attributed to their enhanced feature extraction and cost volume processing capabilities. This comprehensive survey delves into deep-learning-based MVS algorithms, highlighting key challenges and avenues for future exploration. Our focus is on studies aimed at mitigating algorithmic memory requirements and elevating processing speeds. To better understand the developments in this field, we propose a new taxonomy. The deep-learning-based MVS algorithms are categorized into two categories: scene-oriented and view-oriented methods. Scene-oriented methods typically employ voxels or neural implicit representations as the representative form of the scene and infer the complete scene directly. View-oriented methods focus on estimating the depth map of a single view. Detailed classifications and reviews have been conducted for each category. Furthermore, we introduce several widely used datasets and metrics and empirical evaluation of representative algorithms across three popular datasets. This article concludes by discussing prevalent challenges in the MVS domain and promising research directions for the future. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=182975009
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11042-024-20464-9
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 32
        StartPage: 2877
    Subjects:
      – SubjectFull: Stereo image processing
        Type: general
      – SubjectFull: Computer vision
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Depth maps (Digital image processing)
        Type: general
      – SubjectFull: Process capability
        Type: general
      – SubjectFull: Deep learning
        Type: general
    Titles:
      – TitleFull: Multi-view stereo algorithms based on deep learning: a survey.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Huang, Hongbo
      – PersonEntity:
          Name:
            NameFull: Yan, Xiaoxu
      – PersonEntity:
          Name:
            NameFull: Zheng, Yaolin
      – PersonEntity:
          Name:
            NameFull: He, Jiayu
      – PersonEntity:
          Name:
            NameFull: Xu, Longfei
      – PersonEntity:
          Name:
            NameFull: Qin, Dechun
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 21
              M: 02
              Text: Feb2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 13807501
          Numbering:
            – Type: volume
              Value: 84
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Multimedia Tools & Applications
              Type: main
ResultId 1