Definition
Multi-baseline stereo is any number of techniques for computing depth maps from several, typically many, photographs of a scene with known camera parameters.
Background
The goal of any stereo algorithm is to reconstruct the 3D surface geometry of a scene from multiple photographs. Multi-baseline stereo can be seen as a generalization of binocular stereo, and it is one instance of a broader class of multi-view stereo algorithms. The classic binocular stereo problem focuses on using two views of a scene (the minimal case), whereas multi-baseline stereo uses more than two and typically many more views of the scene. More views not only provide a better signal to noise ratio but also eliminate most repetitive structure errors and offer new ways to handle occlusions.
Another type of multi-view stereo is volumetric stereo, which explicitly models the scene’s surface in a volume, and is sometimes called object-based. Multi-baseline stereo on the other hand is image-based, and seeks...
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zabulis X, Daniilidis K (2004) Multi-camera reconstruction based on surface normal estimation and best viewpoint selection. In: Proceedings of the 2nd international symposium on 3D data processing, visualization and transmission (3DPVT), pp 733–740
Gallup D, Frahm J-M, Mordohai P, Yang Q, Pollefeys M (2004) Real-time plane-sweeping stereo with multiple sweeping directions. In: IEEE conference computer vision and pattern recognition (CVPR), Minneapolis
Okutomi M, Kanade T (2002) A multiple-baseline stereo. In: IEEE Trans Pattern Anal Mach Intell, 15(4): 353–363
Kang S, Szeliski R, Chai J (2001) Handling occlusions in dense multi-view stereo. In: IEEE conference computer vision and pattern recognition (CVPR), Kauai
Hernandez C, Vogiatzis G, Cipolla R (2001) Probabilistic visibility for multi-view stereo. In: IEEE conference computer vision and pattern recognition (CVPR), Minneapois
Kolmogorov V, Zabih R (2002) Multi-camera scene reconstruction via graph cuts. In: European conference on computer vision 2002 (ECCV), Copenhagen
Yang R, Pollefeys M (2003) Multi-resolution real-time stereo on commodity graphics hardware. In: IEEE conference on computer vision and pattern recognition (CVPR), Madison
Boykov Y, Veksler O, Zabih R (2001) Fast approximate energy minimization via graph cuts. In: IEEE Trans Pattern Anal Mach Intell, 23(11): 1222–1239
Felzenszwalb P, Huttenlocher D (2001) Efficient belief propagation for early vision. In: IEEE conference on computer vision and pattern recognition (CVPR), Kauai
Gallup D, Frahm J-M, Mordohai P, Pollefeys M (2008) Variable baseline/resolution stereo. In: IEEE conference on computer vision and pattern recognition (CVPR), Anchorage
Pollefeys M, Nister D, Frahm J-M, Akbarzadeh A, Mordohai P, Clipp B, Engels C, Gallup D, Kim S-J, Merrell P, Salmi C, Sinha S, Talton B, Wang L, Yang Q, Stewenius H, Yang R, Welch G, Towles H (2008) Detailed real-time urban 3D reconstruction from video. Int J Comput Vision, 78(2–3): 143–167
Yang R, Pollefeys M, Yang H, Welch G (2003) A unified approach to real-time, multi-resolution, multi-baseline 2D view synthesis and 3D depth estimation using commodity graphics hardware. Int J Image Graph, 4(4): 627–651
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this entry
Cite this entry
Gallup, D. (2014). Multi-baseline Stereo. In: Ikeuchi, K. (eds) Computer Vision. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-31439-6_199
Download citation
DOI: https://doi.org/10.1007/978-0-387-31439-6_199
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30771-8
Online ISBN: 978-0-387-31439-6
eBook Packages: Computer ScienceReference Module Computer Science and Engineering