Rotation constrained power factorization for structure from motion of nonrigid objects

Abstract

The paper addresses the problem of recovering 3D structure and motion of nonrigid objects from image sequences. We propose a rotation constrained power factorization (RCPF) algorithm that combines the orthonormality and the replicated block structure of the motion matrix directly into iterations. The algorithm overcomes some limitations of previous SVD-based methods and can work with missing data. Based on the shape bases of the batch-type factorization, we also propose a sequential factorization technique to recover the shape and motion of new frames conveniently. Extensive experiments show the effectiveness of the proposed algorithm.