Foundations and Trends® in Computer Graphics and Vision > Vol 9 > Issue 1-2

Multi-View Stereo: A Tutorial

Yasutaka Furukawa, Washington University in St. Louis, USA, furukawa@wustl.edu Carlos Hernández, Google Inc., USA, carloshernandez@google.com
 
Suggested Citation
Yasutaka Furukawa and Carlos Hernández (2015), "Multi-View Stereo: A Tutorial", Foundations and Trends® in Computer Graphics and Vision: Vol. 9: No. 1-2, pp 1-148. http://dx.doi.org/10.1561/0600000052

Published: 24 Jun 2015
© 2015 Y. Furukawa and C. Hernández
 
Subjects
3D reconstruction and image-based modeling,  Shape: Surface reconstruction
 
Keywords
Stereo matching and reconstruction
 

Free Preview:

Article Help

Share

Download article
In this article:
1. Introduction
2. Multi-view Photo-consistency
3. Algorithms: From Photo-Consistency to 3D Reconstruction
4. Multi-view Stereo and Structure Priors
5. Software, Best Practices, and Successful Applications
6. Limitations and Future Directions
Acknowledgements
References

Abstract

This tutorial presents a hands-on view of the field of multi-view stereo with a focus on practical algorithms. Multi-view stereo algorithms are able to construct highly detailed 3D models from images alone. They take a possibly very large set of images and construct a 3D plausible geometry that explains the images under some reasonable assumptions, the most important being scene rigidity. The tutorial frames the multiview stereo problem as an image/geometry consistency optimization problem. It describes in detail its main two ingredients: robust implementations of photometric consistency measures, and efficient optimization algorithms. It then presents how these main ingredients are used by some of the most successful algorithms, applied into real applications, and deployed as products in the industry. Finally it describes more advanced approaches exploiting domain-specific knowledge such as structural priors, and gives an overview of the remaining challenges and future research directions.

DOI:10.1561/0600000052
ISBN: 978-1-60198-836-2
164 pp. $99.00
Buy book
 
ISBN: 978-1-60198-837-9
164 pp. $250.00
Buy E-book
Table of contents:
1. Introduction
2. Multi-view Photo-consistency
3. Algorithms: From Photo-Consistency to 3D Reconstruction
4. Multi-view Stereo and Structure Priors
5. Software, Best Practices, and Successful Applications
6. Limitations and Future Directions
Acknowledgements
References

Multi-View Stereo: A Tutorial

Multi-View Stereo: A Tutorial presents a hands-on view of the field of multi-view stereo with a focus on practical algorithms. Multi-view stereo algorithms are able to construct highly detailed 3D models from images alone. They take a possibly very large set of images and construct a 3D plausible geometry that explains the images under some reasonable assumptions, the most important being scene rigidity. Multi-View Stereo: A Tutorial frames the multiview stereo problem as an image/geometry consistency optimization problem. It describes in detail its main two ingredients: robust implementations of photometric consistency measures, and efficient optimization algorithms. It then presents how these main ingredients are used by some of the most successful algorithms, applied into real applications, and deployed as products in the industry. Finally, it describes more advanced approaches exploiting domain-specific knowledge such as structural priors, and gives an overview of the remaining challenges and future research directions.

 
CGV-052