SpringerLink
Log in

Wide Baseline Matching

  • Living reference work entry
  • First Online:
Computer Vision

  • 35 Accesses

Synonyms

Wide field of view stereo matching

Related Concepts

Definition

Wide baseline matching is the process of finding correspondences between two images of the same scene taken from widely separated views.

Background

Finding correspondences between images is a first and crucial step in many image processing applications, such as image registration, 3D reconstruction, object recognition, or robot navigation. As long as the images are taken from more or less the same viewpoint, this task is relatively easy. Indeed, under these conditions (usually referred to as small baseline), the corresponding image patch will look very similar, and also its location in the image will have changed only slightly, so a local search for the most similar image patch suffices to find correspondences.

However, when the baseline between the cameras (i.e., the distance between the camera projection centers) increases, finding correspondences becomes a significantly harder problem. First,...

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

References

  1. Balntas V, Riba E, Ponsa D, Mikolajczyk K (2016) Learning local feature descriptors with triplets and shallow convolutional neural networks. Br Mach Vis Conf pp 119.1–119.11

    Google Scholar 

  2. Bay H, Ferrari V, Van Gool L (2005) Wide-baseline stereo matching with line segments. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), San Diego, vol 1, pp 329–336

    Google Scholar 

  3. Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (SURF). Comput Vis Image Underst 110(3):346–359

    Article  Google Scholar 

  4. DeTone D, Malisiewicz T, Rabinovich A (2018) Superpoint: self-supervised interest point detection and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 224–236

    Google Scholar 

  5. Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24:381–395

    Article  MathSciNet  Google Scholar 

  6. Harris C, Stephens MA (1988) combined corner and edge detector. In: Proceedings of the 4th Alvey vision conference, Manchester, pp 147–151

    Google Scholar 

  7. Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110

    Article  Google Scholar 

  8. Matas J, Chum O, Martin U, Pajdla T (2002) Robust wide baseline stereo from maximally stable extremal regions. In: Proceedings of the British machine vision conference, Cardiff, vol 1, pp 384–393

    Google Scholar 

  9. Mikolajczyk K, Schmid C (2004) Scale and affine invariant interest point detectors. Int J Comput Vis 60(1):63–86

    Article  Google Scholar 

  10. Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A, Matas J, Schaffalitzky F, Kadir T, Van Gool L (2005) A comparison of affine region detectors. Int J Comput Vis 65(1–2):43–72

    Article  Google Scholar 

  11. Moo Yi K, Trulls E, Lepetit V, Fua P (2016) LIFT: learned invariant feature transform. Eur Conf Comput Vis pp 467–483

    Google Scholar 

  12. Moreels P, Perona P (2006) Evaluation of features detectors and descriptors base on 3D objects. Int J Comput Vis 73(3):263–284

    Article  Google Scholar 

  13. Morel JM, Yu G (2009) ASIFT, a new framework for fully affine invariant image comparison. SIAM J Imaging Sci 2(2):438–469

    Article  MathSciNet  Google Scholar 

  14. Ono Y, Trulls E, Fua P, Moo Yi K (2019) LF-Net: learning local features from images. In: Advances neural information processing systems

    Google Scholar 

  15. Savinov N, Seki A, Ladicky L, Sattler T, Pollefeys M (2017) Quad-networks: unsupervised learning to rank for interest point detection. In: IEEE/CVF conference on computer vision and pattern recognition

    Google Scholar 

  16. Simonyan K, Vedaldi A, Zisserman A (2014) Learn Local Feature Descriptors Convex Optim IEEE PAMI 36(8):1573–1585

    Google Scholar 

  17. Simo-Serra E, Trulls E, Ferraz L, Kokkinos I, Fua P, Moreno-Noguer F (2015) Discriminative learning of deep convolutional feature point descriptors. In: International conference on computer vision

    Book  Google Scholar 

  18. Tuytelaars T, Van Gool L (2004) Matching widely separated views based on affine invariant regions. Int J Comput Vis 59(1):61–85

    Article  Google Scholar 

  19. Zhang L, Rusinkiewicz Z (2018) Learning to detect features in texture images. In: IEEE/CVF conference on computer vision and pattern recognition

    Book  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. KULEUVEN, ESAT-PSI, Leuven, Belgium

    Tinne Tuytelaars

Authors
  1. Tinne Tuytelaars
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tinne Tuytelaars .

Section Editor information

  1. ETH Zurich - Microsoft, Zurich, Switzerland

    Marc Pollefeys

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this entry

Check for updates. Verify currency and authenticity via CrossMark

Cite this entry

Tuytelaars, T. (2021). Wide Baseline Matching. In: Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-030-03243-2_191-1

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-03243-2_191-1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-03243-2

  • Online ISBN: 978-3-030-03243-2

  • eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering

Publish with us

Policies and ethics

Search

Navigation