hide
Free keywords:
-
Abstract:
We present a new passive approach to capture time-varying scene geometry in
large acquisition volumes from multi-view video. It can be applied to
reconstruct complete moving models of human actors that feature even slightest
dynamic geometry detail, such as wrinkles and folds in clothing, and that can
be viewed from 360 degrees. Starting from multi-view video streams recorded
under calibrated lighting, we first perform marker-less human motion capture
based on a smooth template with no high-frequency surface detail. Subsequently,
surface reflectance and time-varying normal fields are estimated based on the
coarse template shape. The main contribution of this work is a new statistical
approach to solve the non-trivial problem of transforming the captured normal
field that is defined over the smooth non-planar 3D template into true 3D
displacements. Our spatio-temporal reconstruction method outputs displaced
geometry that is accurate at each time step of video and temporally smooth,
even if the input data are affected by noise.
