Synonyms
Shape from outlines of projection; Visual hull
Related Concepts
Definition
Shape from silhouette (SfS) algorithms compute the (approximate) 3D shape of an object from multiple 2D projections considering only the outline of the object in the projections. The most important class of SfS methods are Visual Hull algorithms.
Background
The problem of computing shape from outlines (silhouettes) of projections is generally underconstrained. Depending on the object's geometry and the number of available views, approximations can be computed which are sufficient for some applications. Often, the SfS output serves as initialization for appearance-based shape reconstruction methods such as volumetric reconstruction or multiview stereo.
The most general class of SfS approaches, where no assumptions about the type of objects to reconstruct are made, are the Visual Hull algorithms (e.g., [1–4]). These are treated in a dedicated article.
If the class of objects to handle is...
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
. Baumgart BG (1974) Geometric modeling for computer vision. PhD thesis, Stanford, Stanford, CA, USA
Ahuja N, Veenstra J (1989) Generating octrees from object silhouettes in orthographic views. IEEE Trans Pattern Anal Mach Intell 11(2):137–149
Laurentini A (1991) The visual hull: a new tool for contour-based image understanding. In: Proceedings of the 7th Scandinavian conference on image analysis. Pattern Recognition Society of Denmark, Aalborg East
Szeliski R (1993) Rapid octree construction from image sequences. CVGIP 58:23–32
Balan AO, Sigal L, Black MJ, Davis JE, Haussecker HW (2007) Detailed human shape and pose from images. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR '07). IEEE, Piscataway, Minneapolis, Minnesota, pp 1–8
Guan P, Weiss A, Balan AO, Black MJ (2009) Estimating human shape and pose from a single image. In: Proceedings of the IEEE 12th International Conference on Computer Vision (ICCV), Kyoto, Japan, pp 1381–1388
Schneider DC, Eisert P (2009) Fast nonrigid mesh registration with a data-driven deformation prior. In: Proceedings of the IEEE 12th international computer vision workshops, Kyoto, Japan, pp 304–311
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this entry
Cite this entry
Schneider, D.C. (2014). Shape from Silhouette. In: Ikeuchi, K. (eds) Computer Vision. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-31439-6_206
Download citation
DOI: https://doi.org/10.1007/978-0-387-31439-6_206
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