Abstract
This paper introduces a new form of representation for three-dimensional video objects. We have developed a technique to extract disparity and texture data from video objects, that are captured simultaneously with multiple-camera configurations. As a result, we obtain the video object plane as an unwrapped surface of a 31) object, containing all texture data visible from any of the cameras. This texture surface can be encoded like any 2D video object plane, while the 3D information is contained in the associated disparity map. It is then possible to reconstruct different viewpoints from the texture surface by simple disparity-based projection. The merits of the technique are efficient multiview encoding of single video objects, and support for viewpoint adaptation functionality, which is desirable in mixing natural and synthetic images. We have performed experiments with the MPEG-4 video verification model, where the disparity map is encoded by use of the tools provided for grayscale alpha data encoding. Due to its simplicity, the technique is capable for applications with requirement for realtime viewpoint adaptation towards video objects.
Preview
Unable to display preview. Download preview PDF.
References
J.-R. Ohm and E. IzquierdoM.: “An object-based system for stereoscopic viewpoint synthesis,” IEEE Trans. Circ. Syst. Video Tech., vol. CSVT-7, no.5, pp. 801–811, Oct. 1997
E. Izquierdo and M. Ernst: “Motion/disparity analysis for 3D-video-conference applications,” Proc. Intern. Workshop on Stereoscopy and 3-Dimensional Imaging (IWS3DI'95), Santorini, Greece, Sept. 1995
O. Faugeras: “Three-Dimensional Computer Vision,” MIT Press, Cambridge, Mass.: 1993
J.-R. Ohm et al.: “A realtime hardware system for stereoscopic video-conferencing with viewpoint adaptation,” to appear in Image Communication, special issue on 3D TV, January 1998
ISO/IEC JTC1/SC29/WG11: “MPEG-4 video verification model version 8.0,” Document no. N1796, July 1997
ISO/IEC JTCI/SC29/WG11: “SNHC Verification Model 3.0,” Document no. N1545, Feb. 1997
“The Moving Worlds proposal for VRML 2.0,” submitted by Silicon Graphics in collaboration with Sony and WorldMaker, May 1996
J.-R. Ohm, K. Müller, C. Stoffers and S. Kruse: “Incomplete 3D representation of video objects,” ISO/IEC JTCl/SC29/WG11, document no. M2639, Oct. 1997
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ohm, JR., Müller, K. (1998). Incomplete 3D for multiview representation and synthesis of video objects. In: Hutchison, D., Schäfer, R. (eds) Multimedia Applications, Services and Techniques — ECMAST'98. ECMAST 1998. Lecture Notes in Computer Science, vol 1425. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-64594-2_83
Download citation
DOI: https://doi.org/10.1007/3-540-64594-2_83
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64594-8
Online ISBN: 978-3-540-69344-4
eBook Packages: Springer Book Archive