Abstract
We discuss challenges in large scale multi-view video capture and use broadcast soccer matches as a motivating application. How far away are we from watching a soccer match at home and changing the virtual viewpoint smoothly from full field views to closeups of individual players, from any angle? We start with a discussion of the total number of pixels required to capture this event for two different kinds of systems: a fixed array of high-resolution cameras, and an active array of low-resolution cameras. Next we look at strategies for increasing the effective frame rate of such systems to allow high-speed capture. Most multi-camera systems are synchronized so all cameras trigger simultaneously, but staggering the triggers samples more efficiently in time, with no additional cost in data bandwidth. We then move from sampling issues to rendering realism and look at one open challenge that is critical for video-based rendering of people: the capture and rendering of moving human hair. Finally, we consider the real-time processing and broadcast of this media for a live soccer match.
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
Argusight. http://argusight.com/ (2009)
Autonomous real-time ground ubiquitous surveillance - imaging system (argus-is) (2009)
Directtv. http://www.directtv.com/ (2009)
Black, M., Anandan, P.: A framework for the robust estimation of optical flow. In: IEEE International Conference on Computer Vision (ICCV), pp. 231–236 (1993)
Bradley, D., Boubekeur, T., Heidrich, W.: Accurate multi-view reconstruction using robust binocular stereo and surface matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2008)
Carnegie mellon goes to the super bowl. http://www.ri.cmu.edu/events/sb35/tksuperbowl.html
Chai, J.X., Tong, X., Chan, S.C., Shum, H.Y.: Plenoptic sampling. In: ACM SIGGRAPH 2000, Proceedings of the 27th Annual Conference on Computer Grapics, pp. 307–318. Orleans, LA, USA (2000)
Grabli, S., Sillion, F., Marschner, S., Lengyel, J.: Image-based hair capture by inverse lighting. In: Proceedings of the Graphics Interface, pp. 51–58 (2002)
Kanade, T., Rander, P., Narayanan, P.: Virtualized reality: constructing virtual worlds from real scenes. IEEE Multimed. 4(1), 34–47 (1997)
Kang, S.B., Uyttendaele, M., Winder, S., Szeliski, R.: High Dynamic Range Video, pp. 319–325 (2003)
Kong, W., Takahashi, H., Nakajima, M.: Generation of 3D hair model from multiple pictures. In: Proceedings of the Multimedia Modeling, pp. 183–196 (1997)
Levoy, M., Hanrahan, P.: Light field rendering. In: Proceedings of the ACM SIGGRAPH’96 (1996)
Magnor, M.: Video-Based Rendering. AK Peters (2005)
Matsuyama, T., Wu, X., Takai, T., Nobuhara, S.: Real-time 3D shape reconstruction, dynamic 3D mesh deformation, and high fidelity visualization for 3D video. Int. J. Comput. Vis. Image Underst. 96(3), 393–434 (2004)
Matusik, W., Buehler, C., Raskar, R., McMillan, L., Gortler, S.: Image-based visual hulls. In: SIGGRAPH 2000 (2000)
Paris, S., Briceno, H.M., Sillion, F.X.: Capture of hair geometry from multiple images. ACM Trans. Graph. 23(3), 712–719 (2004)
Paris, S., Chang, W., Jarosz, W., Kozhushnyan, O., Matusik, W., Zwicker, M., Durand, F.: Hair photobooth: Geometric and photometric acquisition of real hairstyles. ACM Trans. Graph. 27(3) (2008)
Pons, J.P., Keriven, R., Faugeras, O.: Modelling dynamic scenes by registering multi-view image sequences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2005)
Shum, H., Chan, S., Kang, S.B.: Image-Based Rendering. Springer (2007)
Seitz, S., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: Multi-view stereo web page. http://vision.middlebury.edu/mview/
Seitz, S., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and taxonomy of multi-view stereo reconstruction algorithms. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 519–526 (2006)
Sky tv. http://www.sky.com/ (2009)
Starck, J., Hilton, A.: Surface capture for performance based animation. IEEE Comput. Graph. Appl.
Ward, K., Bertails, F., Kim, T., Marschner, S., Cani, M., Lin, M.: A survey on hair modeling: styling, simulation, and rendering. IEEE Trans. Vis. Comput. Graph. 13(2), 213–234 (2007)
Wei, Y., Ofek, E., Quan, L., Shum, H.: Modeling hair from multiple views. ACM Trans. Graph. 24(3), 816–820 (2005)
Wilburn, B., Joshi, N., Vaish, V., Talvala, E., Antunez, E., Barth, A., Adams, A., Horowitz, M., Levoy, M.: High performance imaging using large camera arrays. ACM Trans. Graph. 24(3), 765–776 (2005)
Yamaguchi, T., Wilburn, B., Ofek, E.: Video-based modeling of dynamic hair. In: Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology (PSIVT), Lecture Notes In Computer Science (LNCS), vol. 5414, pp. 585–596. Springer (2009)
Zhao, W.Y., Sawhney, H.S.: Is super-resolution with optical flow feasible? In: Heyden, A., et al. (eds.) Eurorean Conference on Computer Vision (ECCV), LNCS, vol. 2350, pp. 599–613. Springer (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Wilburn, B. (2010). Challenges for Multi-View Video Capture. In: Ronfard, R., Taubin, G. (eds) Image and Geometry Processing for 3-D Cinematography. Geometry and Computing, vol 5. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12392-4_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-12392-4_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12391-7
Online ISBN: 978-3-642-12392-4
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)