Abstract
This paper addresses the problem of obtaining an accurate 3D reconstruction from multiple views. Taking inspiration from the recent successes of using strong prior knowledge for image segmentation, we propose a framework for 3D reconstruction which uses such priors to overcome the ambiguity inherent in this problem. Our framework is based on an object-specific Markov Random Field (MRF)[10]. It uses a volumetric scene representation and integrates conventional reconstruction measures such as photo-consistency, surface smoothness and visual hull membership with a strong object-specific prior. Simple parametric models of objects will be used as strong priors in our framework. We will show how parameters of these models can be efficiently estimated by performing inference on the MRF using dynamic graph cuts [7]. This procedure not only gives an accurate object reconstruction, but also provides us with information regarding the pose or state of the object being reconstructed. We will show the results of our method in reconstructing deformable and articulated objects.
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
Preview
Unable to display preview. Download preview PDF.
References
Bhatia, S., Sigal, L., Isard, M., Black, M.J.: 3d human limb detection using space carving and multi-view eigen models. In: ANM Workshop, vol. I, p. 17 (2004)
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. PAMI 26(9), 1124–1137 (2004)
Boykov, Y.Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. In: ICCV, pp. 105–112 (2001)
Bray, M., Kohli, P., Torr, P.H.S.: Posecut: Simulataneous segmentation and 3d pose estimation of humans using dynamic graph cuts. In: ECCV, pp. 642–655 (2006)
Meijster, et al.: A general algorithm for computing distance transforms in linear time. In: MMAIS Processing, pp. 331–340 (2000)
Press, et al.: Numerical recipes in C. Cambridge Uni. Press, Cambridge (1988)
Kohli, P., Torr, P.: Efficiently solving dynamic markov random fields using graph cuts. In: ICCV (2005)
Kolmogorov, V., Zabih, R.: Multi-camera scene reconstruction via graph cuts. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, p. 82. Springer, Heidelberg (2002)
Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, p. 65. Springer, Heidelberg (2002)
Kumar, M.P., Torr, P.H.S., Zisserman, A.: Obj cut. In: CVPR, vol. I, pp. 18–25 (2005)
Kutulakos, K.N., Seitz, M.: A theory of shape by space carving. IJCVÂ 38(3) (2000)
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV 47(1-3), 7–42 (2002)
Snow, D., Viola, P., Zabih, R.: Exact voxel occupancy with graph cuts. In: CVPR (2000)
Szeliski, R.: Rapid octree construction from image sequences. CVGIP 58, 23–32 (1993)
Vogiatzis, G., Torr, P.H.S., Cipolla, R.: Multi-view stereo via volumetric graph-cuts. In: CVPR, vol. II, pp. 391–398 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sun, Y., Kohli, P., Bray, M., Torr, P.H.S. (2006). Using Strong Shape Priors for Stereo. In: Kalra, P.K., Peleg, S. (eds) Computer Vision, Graphics and Image Processing. Lecture Notes in Computer Science, vol 4338. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11949619_79
Download citation
DOI: https://doi.org/10.1007/11949619_79
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-68301-8
Online ISBN: 978-3-540-68302-5
eBook Packages: Computer ScienceComputer Science (R0)