Exploitation of 3D video technologies

3D video is not an artificial CG animation but a real 3D movie recording the full 3D shape, motion, and precise surface color & texture of real world objects. It enables us to observe real object behaviors from any viewpoints as well as to see pop-up 3D object images. We believe the exploitation of 3D video technologies will open up a new world of versatile cultural and social activities: visual communication, entertainment, training & learning, archiving, and so on. We give an overview of our research attainments so far obtained: (1) a PC cluster system with distributed active cameras for real-time 3D shape reconstruction, (2) a dynamic 3D mesh deformation method for obtaining accurate 3D object shape, (3) a texture mapping algorithm for high fidelity visualization, and (4) user friendly 3D video editing system.

[1]  Xiaojun Wu,et al.  Real-time 3D shape reconstruction, dynamic 3D mesh deformation, and high fidelity visualization for 3D video , 2004, Comput. Vis. Image Underst..

[2]  Atsushi Imiya,et al.  Marching cubes method with connectivity , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[3]  Saied Moezzi,et al.  Virtual View Generation for 3D Digital Video , 1997, IEEE Multim..

[4]  Takashi Matsuyama,et al.  Generation, visualization, and editing of 3D video , 2002, Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission.

[5]  Xiaojun Wu,et al.  Real-time dynamic 3-D object shape reconstruction and high-fidelity texture mapping for 3-D video , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Xiaojun Wu,et al.  Homography based parallel volume intersection: toward real-time volume reconstruction using active cameras , 2000, Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception.

[7]  Takashi Matsuyama,et al.  Appearance sphere: background model for pan-tilt-zoom camera , 1996, Proceedings of 13th International Conference on Pattern Recognition.