Abstract
In this talk, we introduce the outline of gThe MR-PreViz Projecth performed in Japan. In the pre-production process of filmmaking, PreViz, pre-visualizing the desired scene by CGI, is used as a new technique. In its advanced approach, we propose MR-PreViz to utilize mixed reality technology as in current PreViz. MR-PreViz makes it possible to merge the real background and the computer-generated humans and creatures in an open set or at an outdoor location. Computer vision technologies are required for many aspects of MR-PreViz. For capturing an actor’s action, we applied 3D Video, which is a technology that allows one to reconstruct an image seen from any viewpoint in real time from video images taken by multiple cameras. As the other application of CV, we developed a vision based camera tracking method. The method collects environmental information required for tracking efficiently using a structure-from-motion technique before the shooting. Additionally, we developed a relighting technique for lighting design of MR-PreViz movie.
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
Tamura, H., Yamamoto, H., Katayama, A.: Mixed reality: Future dreams seen at the border between real and virtual worlds. IEEE Computer Graphics & Applications 21, 64–70 (2001)
Tenmoku, R., Ichikari, R., Shibata, F., Kimura, A., Tamura, H.: Design and prototype implementation of MR pre-visualization workflow. In: DVD-ROM Proc. Int. Workshop on Mixed Reality Technology for Filmmaking, pp. 26–30 (2006)
Ichikari, R., Tenmoku, R., Shibata, F., Ohshima, T., Tamura, H.: Mixed reality pre-visualization for filmmaking: On-set camera-work authoring and action rehearsal. Int. J. Virtual Reality 7, 25–32 (2008)
Starck, J., Maki, A., Nobuhara, S., Hilton, A., Matsuyama, T.: The multiple-camera 3-D production studio. IEEE Trans. on Circuits and Systems for Video Technology 19, 856–869 (2009)
Yamaguchi, T., Nobuhara, S., Matsuyama, T.: Cell-based object tracking method for 3D shape reconstruction using multi-viewpoint active cameras. In: IEEE Int. Workshop on Visual Surveillance, VS 2009 (2009)
Mukasa, T., Miyamoto, A., Nobuhara, S., Maki, A., Matsuyama, T.: Complex human motion estimation using visibility. In: IEEE Int. Conf. Series on Automatic Face and Gesture Recognition (2008)
Klein, G., Murray, D.: Parallel tracking and ma pping for small AR workspaces. In: Proc. ISMAR, pp. 225–234 (2007)
Taketomi, T., Sato, T., Yokoya, N.: Real-time geometric registration using feature landmark database for augmented reality applications. In: Proc. SPIE (2009) 723804–723804–9
Sato, T., Ikeda, S., Yokoya, N.: Extrinsic camera parameter recovery from multiple image sequences captured by an omni-directional multi-camera system. In: Proc. European Conf. on Computer Vision, vol. 2, pp. 326–340 (2004)
Toishita, W., Momoda, Y., Tenmoku, R., Shibata, F., Tamura, H., Taketomi, T., Sato, T., Yokoya, N.: A novel approach to on-site camera calibration and tracking for MR pre-visualization procedure. In: Proc. Human-Computer Interaction International (HCI 2009), pp. 492–502 (2009)
Debevec, P.: Virtual cinematography: Relighting through computation. IEEE Computer 39, 57–65 (2006)
Ichikari, R., Hatano, R., Ohshima, T., Shibata, F., Tamura, H.: Designing cinematic lighting by relighting in MR-based pre-visualization. In: ACM SIGGRAPH ASIA 2009 Posters (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tamura, H., Matsuyama, T., Yokoya, N., Ichikari, R., Nobuhara, S., Sato, T. (2011). Computer Vision Technology Applied to MR-Based Pre-visualization in Filmmaking. In: Koch, R., Huang, F. (eds) Computer Vision – ACCV 2010 Workshops. ACCV 2010. Lecture Notes in Computer Science, vol 6469. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22819-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-22819-3_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22818-6
Online ISBN: 978-3-642-22819-3
eBook Packages: Computer ScienceComputer Science (R0)