%0 Conference Paper %1 ahmed_dense_2008 %A Ahmed, N. %A Theobalt, C. %A Rossl, C. %A Thrun, S. %A Seidel, H. P %B Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on %D 2008 %K multi\_view deformable\_surface mesh\_consistency %P 1–8 %R 10.1109/CVPR.2008.4587758 %T Dense correspondence finding for parametrization-free animation reconstruction from video %U http://dx.doi.org/10.1109/CVPR.2008.4587758 %X We present a dense 3D correspondence finding method that enables spatio-temporally coherent reconstruction of surface animations from multi-view video data. Given as input a sequence of shape-from-silhouette volumes of a moving subject that were reconstructed for each time frame individually, our method establishes dense surface correspondences between subsequent shapes independently of surface discretization. This is achieved in two steps: first, we obtain sparse correspondences from robust optical features between adjacent frames. Second, we generate dense correspondences which serve as map between respective surfaces. By applying this procedure subsequently to all pairs of time steps we can trivially align one shape with all others. Thus, the original input can be reconstructed as a sequence of meshes with constant connectivity and small tangential distortion. We exemplify the performance and accuracy of our method using several synthetic and captured real-world sequences.

@inproceedings{ahmed_dense_2008, abstract = {We present a dense {3D} correspondence finding method that enables spatio-temporally coherent reconstruction of surface animations from multi-view video data. Given as input a sequence of shape-from-silhouette volumes of a moving subject that were reconstructed for each time frame individually, our method establishes dense surface correspondences between subsequent shapes independently of surface discretization. This is achieved in two steps: first, we obtain sparse correspondences from robust optical features between adjacent frames. Second, we generate dense correspondences which serve as map between respective surfaces. By applying this procedure subsequently to all pairs of time steps we can trivially align one shape with all others. Thus, the original input can be reconstructed as a sequence of meshes with constant connectivity and small tangential distortion. We exemplify the performance and accuracy of our method using several synthetic and captured real-world sequences.}, added-at = {2009-09-29T19:54:20.000+0200}, author = {Ahmed, N. and Theobalt, C. and Rossl, C. and Thrun, S. and Seidel, H. P}, biburl = {https://www.bibsonomy.org/bibtex/257fc2659dd67191a72ecdfa3316de309/dudemeister}, booktitle = {Computer Vision and Pattern Recognition, 2008. {CVPR} 2008. {IEEE} Conference on}, doi = {10.1109/CVPR.2008.4587758}, interhash = {74c3f4237ea61e014176ec4514acc1d9}, intrahash = {57fc2659dd67191a72ecdfa3316de309}, keywords = {multi\_view deformable\_surface mesh\_consistency}, pages = {1–8}, timestamp = {2009-09-29T19:54:20.000+0200}, title = {Dense correspondence finding for parametrization-free animation reconstruction from video}, url = {http://dx.doi.org/10.1109/CVPR.2008.4587758}, year = 2008 }