摘要: We develop a computer vision-based system to transfer human motion from one subject another. Our uses network of eight calibrated and synchronized cameras. first build detailed kinematic models the subjects based on our algorithms for extracting shape silhouette across time (G. Cheung et al., 2003). These are then used capture (joint angles) in new video sequences. Finally we describe an image-based rendering algorithm render captured applied articulated model another person. ensemble spatially temporally distributed images generate photo-realistic transferred motion. demonstrate performance by throwing kungfu motions who did not perform them.
ieeecomputersociety.org参考文章(15)
J. Blinn, Me and My (Fake) Shadow IEEE Computer Graphics and Applications. ,vol. 8, pp. 82- 86 ,(1988)
Paul E. Debevec, Camillo J. Taylor, Jitendra Malik, Modeling and rendering architecture from photographs: a hybrid geometry- and image-based approach international conference on computer graphics and interactive techniques. pp. 11- 20 ,(1996) , 10.1145/237170.237191
Hank Weghorst, Gary Hooper, Donald P. Greenberg, Improved Computational Methods for Ray Tracing ACM Transactions on Graphics. ,vol. 3, pp. 52- 69 ,(1984) , 10.1145/357332.357335
Q. Delamarre, O. Faugeras, 3D articulated models and multi-view tracking with silhouettes international conference on computer vision. ,vol. 2, pp. 716- 721 ,(1999) , 10.1109/ICCV.1999.790292
Thomas B. Moeslund, Erik Granum, A Survey of Computer Vision-Based Human Motion Capture Computer Vision and Image Understanding. ,vol. 81, pp. 231- 268 ,(2001) , 10.1006/CVIU.2000.0897
P. Rander, R. Collins, T. Kanade, Three-dimensional scene flow international conference on computer vision. ,vol. 2, pp. 722- 729 ,(1999) , 10.1109/ICCV.1999.790293
J.F. Blinn, Vectors and geometry and objects, oh my! IEEE Computer Graphics and Applications. ,vol. 25, pp. 84- 93 ,(2005) , 10.1109/MCG.2005.69
Simon Baker, Takeo Kanade, Sundar Vedula, Spatio-temporal view interpolation eurographics. pp. 65- 76 ,(2002) , 10.5555/581896.581906
H. Sidenbladh, F. De la Torre, M.J. Black, A framework for modeling the appearance of 3D articulated figures ieee international conference on automatic face and gesture recognition. pp. 368- 375 ,(2000) , 10.1109/AFGR.2000.840661
G.K.M. Cheung, S. Baker, T. Kanade, Visual hull alignment and refinement across time: a 3D reconstruction algorithm combining shape-from-silhouette with stereo computer vision and pattern recognition. ,vol. 2, pp. 375- 382 ,(2003) , 10.1109/CVPR.2003.1211493