Abstract
This paper develops a multi-view stereo approach to reconstruct the shape of a three-dimensional object from a set of Internet photos. The stereo matching technique adopts region growing approach, starting from a set of sparse three-dimensional points reconstructed from structure-from-motion (Sfm), then propagates to the neighbouring areas by the best-first strategy, and produces dense three-dimensional points. We demonstrate our algorithms that they perform robustly.
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
Furukawa Y, Ponce J (2007) Accurate, dense, and robust multi-view stereopsis. Proc CVPR 20(3):487–493
Zhao J, Wang Q, Wang X (2006) The real-time three-dimensional animation of highway that based on the digital terrain model. Comput Eng 31(12):196–199
Goesele M, Snavely N, Curless B, Hoppe H, Seitz SM (2007) Multi-view stereo for community photo collections. ICCV 92(4):198–207
Liu Y, Li J, Huang J et al (2005) Establish the three-dimensional road model from the plan and transverse section. J Huazhong Univ Sci Technol (Urban Science Edition) 22:156–158
Otto GP, Chau TKW (1989) ‘Region-Growing’ algorithm for matching of terrain images. Image Vision Comput 7(2):83–94
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag London
About this paper
Cite this paper
Wang, Z. (2013). Research of Multi-View Stereo Reconstruction for Internet Photos. In: Du, W. (eds) Informatics and Management Science VI. Lecture Notes in Electrical Engineering, vol 209. Springer, London. https://doi.org/10.1007/978-1-4471-4805-0_6
Download citation
DOI: https://doi.org/10.1007/978-1-4471-4805-0_6
Publisher Name: Springer, London
Print ISBN: 978-1-4471-4804-3
Online ISBN: 978-1-4471-4805-0
eBook Packages: EngineeringEngineering (R0)