Motion Reconstruction

The goal of this thesis was to reconstruct realistic hand motions in the presence of noise and occlusions. In the first part of this work, we process multi-view RGB input sequences with off-the-shelf methods to get a robust, but noisy MANO motion estimate. For the second part we split the estimation of the global and local features. As datasets covering both diverse global and local hand motion do not currently exist, we learn the dynamics of the two parts in isolation....