Abstract
Time-varying mesh (TVM) is a technique that describes full shape and motion of a real-world moving object. Thus, TVM is used to capture and reproduce human behavior and natural movements precisely, such as the expression of the face or small changes in cloths. But on the other hand, TVM requires large storage space and computational cost. To solve this problem, we propose a framework of motion editing and synthesis. In our approach, a skeleton model is extracted from each frame and motion tracking and analysis are conducted using the skeleton models. Then, a representative frame is deformed based on the extracted motion information. As a result, 3D scene representation with much smaller data size is made possible.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Matsuyama, T., Wu, X., Takai, T., Wada, T.: Real-Time Dynamic 3-D Object Shape Reconstruction and High-Fidelity Texture Mapping for 3-D Video. IEEE Trans. CSVT 14(3), 357–369 (2004)
Tomiyama, K., Orihara, Y., Katayama, M., Iwadate, Y.: Algorithm for dynamic 3D object generation from multi-viewpoint images. In: Proc. SPIE, vol. 5599, pp. 153–161 (2004)
Kanade, T., Rander, P., Narayanan, P.: Virtualized reality: Construction Virtual Worlds from Real Scenes. IEEE Multimedia 4(1), 34–47 (1997)
Hoppe, H.: Progressive Meshes. In: Proc. SIGGRAPH, pp. 99–108 (1996)
Han, S., Yamasaki, T., Aizawa, K.: Time-varying Mesh Compression Using Extended Block Matching Algorithm. IEEE Transactions on Circuit and Systems for Video Technology 17(11), 1506–1518 (2007)
Xu, J., Yamasaki, T., Aizawa, K.: Deformation of time-varying-mesh based on semantic human model. In: Proc. IEEE ICME 2007, pp. 1700–1703 (2007)
Tung, T., Schmitt, F., Matsuyama, T.: Topology Matching for 3D Video Compression. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), Minneapolis, MN, USA, pp. 1–8 (2007)
Hilaga, M., Shinagawa, Y., Kohmura, T., Kunii, T.L.: Topology matching for fullyautomatic similarity estimation of 3d shapes. In: Proc. SIGGRAPH 2001, pp. 203–212 (2001)
Tadano, R., Yamasaki, T., Aizawa, K.: Fast and robust motion tracking for time-varying mesh featuring Reeb-graph-based skeleton fitting and its application to motion retrieval. In: Proceedings of 2007 IEEE International Conference on Multimedia and Expo (ICME 2007), Beijing, China, July 2-5, pp. 2010–2013 (2007)
Lee, N.S., Yamasaki, T., Aizawa, K.: Hierarchical mesh decomposition and motion tracking for time-varying-meshes. In: Proc. 2008 IEEE International Conference on Multimedia & Expo (ICME 2008), Hannover, Germany, July 23-26 (2008)
Lee, N.S., Yamasaki, T., Aizawa, K.: Motion Tracking Through Surface Gradient Matching for Time-Varying Mesh. In: Meeting on Image Understanding 2008 (MIRU 2008), Nagano, Japan, July 29-31 (to be presented, 2008)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Maeda, T., Yamasaki, T., Aizawa, K. (2008). Model-Based Analysis and Synthesis of Time-Varying Mesh. In: Perales, F.J., Fisher, R.B. (eds) Articulated Motion and Deformable Objects. AMDO 2008. Lecture Notes in Computer Science, vol 5098. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70517-8_12
Download citation
DOI: https://doi.org/10.1007/978-3-540-70517-8_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-70516-1
Online ISBN: 978-3-540-70517-8
eBook Packages: Computer ScienceComputer Science (R0)