View-Independent Enhanced 3D Reconstruction of Non-Rigidly Deforming Objects

In this paper, we target enhanced 3D reconstruction of non-rigidly
deforming objects based on a view-independent surface representation with an
automated recursive filtering scheme. This work improves upon the KinectDeform
algorithm which we recently proposed. KinectDeform uses an implicit viewdependent
volumetric truncated signed distance function (TSDF) based surface
representation. The view-dependence makes its pipeline complex by requiring
surface prediction and extraction steps based on camera’s field of view. This paper
proposes to use an explicit projection-based Moving Least Squares (MLS)
surface representation from point-sets. Moreover, the empirical weighted filtering
scheme in KinectDeform is replaced by an automated fusion scheme based
on a Kalman filter. We analyze the performance of the proposed algorithm both
qualitatively and quantitatively and show that it is able to produce enhanced and
feature preserving 3D reconstructions.