Abstract
3D shape reconstruction has been a major research topic in computer vision and a variety of different algorithms have been developed. This chapter first defines a computational model for 3D video production, followed by an overview of Shape from X methods to investigate practically useful visual cues for 3D shape reconstruction from multi-view video data. Then, we categorize 3D shape reconstruction methods for 3D video production into three types and analyze their computational characteristics: (1) frame-wise 3D shape reconstruction, (2) simultaneous 3D shape and motion estimation, and (3) 3D shape sequence estimation. The computational characteristic analysis leads us to the three essential design factors for 3D shape reconstruction algorithms: (1) photo-consistency, (2) visibility evaluation, and (3) shape representation with corresponding computational model for optimization. Based on these design factors, we implemented several practical algorithms for frame-wise 3D shape reconstruction and simultaneous 3D shape and motion reconstruction. Their performance is evaluated quantitatively with synthesized data as well as qualitatively with real world multi-view video data of MAIKO dance and Yoga performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The projection in computer tomography is characterized as an integral projection where rays go through the interior area of an object and their degrees of attenuation are observed in projected data. In computer vision, most of objects in the real world are non-transparent and reflect light rays at their surfaces. Thus the projection in computer vision implies ray blocking or shadowing.
- 2.
The reasons for this will be discussed later in this chapter.
- 3.
An earlier version can be found in the voxel coloring study by Seitz and Dyer in 1997 [44].
References
Alexa, M., Behr, J., Cohen-Or, D., Fleishman, S., Levin, D., Silva, C.T.: Point set surfaces. In: The Conference on Visualization, pp. 21–28 (2001)
Barr, A.H.: Rigid Physically Based Superquadrics, pp. 137–159. Academic Press, San Diego (1992)
Baumgart, B.G.: Geometric modeling for computer vision. Technical Report AIM-249, Artificial Intelligence Laboratory, Stanford University (1974)
Baumgart, B.G.: A polyhedron representation for computer vision. In: Proceedings of the National Computer Conference and Exposition, AFIPS’75, pp. 589–596 (1975)
Campbell, N., Vogiatzis, G., Hernández, C., Cipolla, R.: Automatic 3D object segmentation in multiple views using volumetric graph-cuts. Image Vis. Comput. 28(1), 14–25 (2010)
Virtualizing Engine. Private communication with Profs. Takeo Kanade and Yaser Sheikh, Robotics Institute, Carnegie Mellon University, PA (2011)
Cremers, D., Kolev, K.: Multiview stereo and silhouette consistency via convex functionals over convex domains. IEEE Trans. Pattern Anal. Mach. Intell., 1161–1174 (2010)
Felzenszwalb, P., Huttenlocher, D.: Efficient belief propagation for early vision. Int. J. Comput. Vis. 70, 41–54 (2006)
Franco, J.-S., Boyer, E.: Efficient polyhedral modeling from silhouettes. IEEE Trans. Pattern Anal. Mach. Intell. 31(3), 414–427 (2009)
Fua, P., Leclerc, Y.G.: Using 3-dimensional meshes to combine image-based and geometry-based constraints. In: Proc. of European Conference on Computer Vision, pp. 281–291 (1994)
Furukawa, Y., Ponce, J.: Accurate, dense, and robust multi-view stereopsis. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)
Goldlüecke, B., Magnor, M.: Space-time isosurface evolution for temporally coherent 3D reconstruction. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 350–355 (2004)
Habbecke, M., Kobbelt, L.: A surface-growing approach to multi-view stereo reconstruction. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)
Hernandez, C., Vogiatzis, G., Cipolla, R.: Probabilistic visibility for multi-view stereo. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)
Hernandez Esteban, C., Vogiatzis, G., Cipolla, R.: Multiview photometric stereo. IEEE Trans. Pattern Anal. Mach. Intell. 30, 548–554 (2008)
Horn, B.K.P., Brooks, M.J.: Shape from Shading. MIT Press, Cambridge (1989)
Hornung, A., Kobbelt, L.: Robust and efficient photo-consistency estimation for volumetric 3d reconstruction. In: Proc. of ECCV, pp. 179–190 (2006)
Ikeuchi, K.: Shape from regular patterns. Artif. Intell. 22(1), 49–75 (1984)
Ikeuchi, K., Oishi, T., Takamatsu, J., Sagawa, R., Nakazawa, A., Kurazume, R., Nishino, K., Kamakura, M., Okamoto, Y.: The great Buddha project: digitally archiving, restoring, and analyzing cultural heritage objects. Int. J. Comput. Vis. 75, 189–208 (2007)
Ishikawa, H.: Higher-order clique reduction in binary graph cut. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2993–3000 (2009)
Kanade, T., Rander, P., Narayanan, P.J.: Virtualized reality: constructing virtual worlds from real scenes. In: IEEE Multimedia, pp. 34–47 (1997)
Kang, S.B., Webb, J.A., Zitnick, C.L., Kanade, T.: A multibaseline stereo system with active illumination and real-time image acquisition. In: Proc. of International Conference on Computer Vision, pp. 88–93 (1995)
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: active contour models. Int. J. Comput. Vis. 1(4), 321–331 (1988)
Kazhdan, M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: Symposium on Geometry Processing, pp. 61–70 (2006)
Kolmogorov, V., Zabih, R.: What energy functions can be minimizedvia graph cuts? IEEE Trans. Pattern Anal. Mach. Intell. 26, 147–159 (2004)
Kutulakos, K.N., Seitz, S.M.: A theory of shape by space carving. In: Proc. of International Conference on Computer Vision, pp. 307–314 (1999)
Laurentini, A.: The visual hull concept for silhouette-based image understanding. IEEE Trans. Pattern Anal. Mach. Intell. 16(2), 150–162 (1994)
Lazebnik, S., Furukawa, Y., Ponce, J.: Projective visual hulls. Int. J. Comput. Vis. 74, 137–165 (2007)
Lempitsky, V., Boykov, Y., Ivanov, D., Ivanov, D.: Oriented visibility for multiview reconstruction. In: Proc. of European Conference on Computer Vision, pp. 226–238 (2006)
Marr, D.: Vision. W. H. Freeman & Co, New York (1982)
Martin, W.N., Aggarwal, J.K.: Volumetric description of objects from multiple views. IEEE Trans. Pattern Anal. Mach. Intell. 5(2), 150–158 (1983)
Matsuyama, T., Wu, X., Takai, T., Nobuhara, S.: Real-time 3D shape reconstruction, dynamic 3D mesh deformation and high fidelity visualization for 3D video. Comput. Vis. Image Underst. 96, 393–434 (2004)
Miller, G., Hilton, A.: Safe hulls. In: Proc. 4th European Conference on Visual Media Production, IET (2007)
Moezzi, S., Tai, L.-C., Gerard, P.: Virtual view generation for 3D digital video. In: IEEE Multimedia, pp. 18–26 (1997)
Nagel, H.H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans. Pattern Anal. Mach. Intell. 8, 565–593 (1986)
Nayar, S.K., Nakagawa, Y.: Shape from focus. IEEE Trans. Pattern Anal. Mach. Intell. 16, 824–831 (1994)
Nayar, S.K., Watanabe, M., Noguchi, M.: Real-time focus range sensor. IEEE Trans. Pattern Anal. Mach. Intell. 18, 1186–1198 (1996)
Nobuhara, S., Matsuyama, T.: Dynamic 3D shape from multi-viewpoint images using deformable mesh models. In: Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis, pp. 192–197 (2003)
Nobuhara, S., Matsuyama, T.: Heterogeneous deformation model for 3D shape and motion recovery from multi-viewpoint images. In: Proc. of International Symposium on 3D Data Processing, Visualization and Transmission, pp. 566–573 (2004)
Nobuhara, S., Matsuyama, T.: Deformable mesh model for complex multi-object 3D motion estimation from multi-viewpoint video. In: Proc. of International Symposium on 3D Data Processing, Visualization and Transmission, pp. 264–271 (2006)
Nobuhara, S., Matsuyama, T.: A 3D deformation model for complex 3D shape and motion estimation from multi-viewpoint video. IEICE Trans. Inf. Syst. J91-D(6), 1613–1624 (2008) (in Japanese)
Nobuhara, S., Tsuda, Y., Ohama, I., Matsuyama, T.: Multi-viewpoint silhouette extraction with 3D context-aware error detection, correction, and shadow suppression. IPSJ Trans. Comput. Vis. Appl. 1, 242–259 (2009)
Okutomi, M., Kanade, T.: A multiple-baseline stereo. IEEE Trans. Pattern Anal. Mach. Intell. 15(1), 353–363 (1993)
Seitz, S., Dyer, C.: Photorealistic scene reconstruction by voxel coloring. Int. J. Comput. Vis. 25(3), 151–173 (1999)
Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 519–528 (2006)
Sinha, S.N., Mordohai, P., Pollefeys, M.: Multi-view stereo via graph cuts on the dual of an adaptive tetrahedral mesh. In: Proc. of International Conference on Computer Vision, pp. 1–8 (2007)
Starck, J., Hilton, A.: Surface capture for performance based animation. IEEE Comput. Graph. Appl. 27(3), 21–31 (2007)
Starck, J., Hilton, A., Miller, G.: Volumetric stereo with silhouette and feature constraints. In: Proc. of British Machine Vision Conference, pp. 1189–1198 (2006)
Starck, J., Maki, A., Nobuhara, S., Hilton, A., Matsuyama, T.: The multiple-camera 3-d production studio. IEEE Trans. Circuits Syst. Video Technol. 19(6), 856–869 (2009)
Subbarao, M., Surya, G.: Depth from defocus: a spatial domain approach. Int. J. Comput. Vis. 13, 271–294 (1994)
Szeliski, R.: Rapid octree construction from image sequences. CVGIP, Image Underst. 58(1), 23–32 (1993)
Tomasi, C., Kanade, T.: Shape and motion from image streams: a factorization method—full report on the orthographic case. Int. J. Comput. Vis. 9, 137–154 (1992)
Tran, S., Davis, L.: 3d surface reconstruction using graph cuts with surface constraints. In: Proc. of European Conference on Computer Vision, vol. 3952, pp. 219–231 (2006)
Tung, T., Schmitt, F.: The augmented multiresolution reeb graph approach for content-based retrieval of 3D shapes. Int. J. Shape Model. 11(1), 91–120 (2005)
Vedula, S., Baker, S., Seitz, S., Kanade, T.: Shape and motion carving in 6D. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition (2000)
Vogiatzis, G., Hernandez, C., Torr, P., Cipolla, R.: Multiview stereo via volumetric graph-cuts and occlusion robust photo-consistency. IEEE Trans. Pattern Anal. Mach. Intell. 29(12), 2241–2246 (2007)
Vogiatzis, G., Torr, P., Seitz, S.M., Cipolla, R.: Reconstructing relief surfaces. In: Proc. of British Machine Vision Conference, pp. 117–126 (2004)
Vogiatzis, G., Torr, P., Cipolla, R.: Multi-view stereo via volumetric graph-cuts. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 391–398 (2005)
Wada, T., Ukida, H., Matsuyama, T.: Shape from shading with interreflections under a proximal light source: distortion-free copying of an unfolded book. Int. J. Comput. Vis. 24(2), 125–135 (1997)
Wu, X.: Parallel pipeline volume intersection for real-time 3D shape reconstruction on a PC cluster. PhD thesis, Kyoto University (March 2005)
Zaharescu, A., Boyer, E., Horaud, R.: Transformesh: a topology-adaptive mesh-based approach to surface evolution. In: Proc. of Asian Conference on Computer Vision, pp. 166–175 (2007)
Zeng, G., Quan, L.: Silhouette extraction from multiple images of an unknown background. In: Proc. of Asian Conference on Computer Vision, pp. 628–633 (2004)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag London
About this chapter
Cite this chapter
Matsuyama, T., Nobuhara, S., Takai, T., Tung, T. (2012). 3D Shape Reconstruction from Multi-view Video Data. In: 3D Video and Its Applications. Springer, London. https://doi.org/10.1007/978-1-4471-4120-4_4
Download citation
DOI: https://doi.org/10.1007/978-1-4471-4120-4_4
Publisher Name: Springer, London
Print ISBN: 978-1-4471-4119-8
Online ISBN: 978-1-4471-4120-4
eBook Packages: Computer ScienceComputer Science (R0)