hide
Free keywords:
-
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.
