Abstract
We present a method for estimating the 3D visual hull of an object from a known class given a single silhouette or sequence of silhouettes observed from an unknown viewpoint. A non-parametric density model of object shape is learned for the given object class by collecting multi-view silhouette examples from calibrated, though possibly varied, camera rigs. To infer a 3D shape from a single input silhouette, we search for 3D shapes which maximize the posterior given the observed contour. The input is matched to component single views of the multi-view training examples. A set of viewpoint-aligned virtual views are generated from the visual hulls corresponding to these examples. The most likely visual hull for the input is then found by interpolating between the contours of these aligned views. When the underlying shape is ambiguous given a single view silhouette, we produce multiple visual hull hypotheses; if a sequence of input images is available, a dynamic programming approach is applied to find the maximum likelihood path through the feasible hypotheses over time. We show results of our algorithm on real and synthetic images of people.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Baumberg, A., Hogg, D.: An adaptive eigenshape model. In: BMVC (1995)
Brand, M.: Shadow puppetry. In: ICCV (1999)
Cheung, G.K.M., Baker, S., Kanade, T.: Shape-From-Silhouette of articulated objects and its use for human body kinematics estimation and motion capture. In: CVPR (2003)
Cipolla, R., Blake, A.: Surface shape from the deformation of apparent contours. IJCV 9(2) (1992)
Cootes, T., Taylor, C.: A mixture model for representing shape variation. In: BMVC (1997)
Curious Labs, Egisys Co. Poser 5: The ultimate 3D character solution
Forsyth, D., Ponce, J.: Computer Vision: A Modern Approach, pp. 552–554 (2003)
Gavrila, D., Philomin, V.: Real-time object detection for smart vehicles. In: ICCV (1999)
Grauman, K., Darrell, T.: Fast contour matching using approximate earth mover’s distance. In: CVPR (2004)
Grauman, K., Shakhnarovich, G., Darrell, T.: Inferring 3D structure with a statistical image-based shape model. In: ICCV (2003)
Grauman, K., Shakhnarovich, G., Darrell, T.: A Bayesian approach to image-based visual hull reconstruction. In: CVPR (2003)
Huttenlocher, D., Klanderman, G., Rucklidge, W.: Comparing images using the Hausdorff distance. In: PAMI (1993)
Jones, M., Poggio, T.: Multidimensional morphable models. In: ICCV (1998)
Laurentini, A.: The visual hull concept for silhouette-based image understanding. PAMI 16(2) (1994)
Lazebnik, S., Boyer, E., Ponce, J.: On computing exact visual hulls of solids bounded by smooth surfaces. In: CVPR (2001)
Matusik, W., Buehler, C., McMillan, L.: Polyhedral visual hulls for real-time rendering. In: EGWR (2001)
Mori, G., Malik, J.: Estimating human body configurations using shape context matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 666–680. Springer, Heidelberg (2002)
Rosales, R., Sclaroff, S.: Specialized mappings and the estimation of body pose from a single image. In: HUMO (2000)
Szeliski, R., Weiss, R.: Robust shape recovery from occluding contours using a linear smoother. IJCV 28(1) (1998)
Toyama, K., Blake, A.: Probabilistic Exemplar-based tracking in a metric space. In: ICCV (2001)
Wong, K.-Y.K., Cipolla, R.: Structure and motion from silhouettes. In: ICCV (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Grauman, K., Shakhnarovich, G., Darrell, T. (2004). Virtual Visual Hulls: Example-Based 3D Shape Inference from Silhouettes. In: Comaniciu, D., Mester, R., Kanatani, K., Suter, D. (eds) Statistical Methods in Video Processing. SMVP 2004. Lecture Notes in Computer Science, vol 3247. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30212-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-540-30212-4_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23989-5
Online ISBN: 978-3-540-30212-4
eBook Packages: Springer Book Archive