A Closed-Form Uncertainty Propagation in Non-Rigid Structure from Motion

Semi-Definite Programming (SDP) with low-rank prior has been widely applied in Non-Rigid Structure from Motion (NRSfM). Based on a constraint, it avoids the inherent ambiguity of basis number selection conventional base-shape or base-trajectory methods. Despite efficiency deformable shape reconstruction, remains unclear how to assess uncertainty recovered SDP process. In this paper, we present statistical inference element-wise quantification estimated deforming 3D points case exact problem. A closed-form method is proposed and tested. Moreover, extend approximate scenario numerical optimal rank method, which enables solving practical application based NRSfM scenario. The provides an independent module only requires statistic information input 2D tracked points. Extensive experiments prove that output have identical normal distribution trackings, quantify accurately, supports desirable effects routinely solver.