A Simple Prior-Free Method for Non-rigid Structure-from-Motion Factorization

摘要

This paper proposes a simple “prior-free” method for solving the non-rigid structure-from-motion (NRSfM) factorization problem.Other than using the fundamental loworder linear combinationmodel assumption, our method does not assume any extra prior knowledge either about the nonrigid structure or about the camera motions. Yet, it works effectively and reliably, producing optimal results, and not suffering from the inherent basis ambiguity issuewhich plagued most conventional NRSfM factorization methods. Our method is very simple to implement, which involves solving a very small SDP (semi-definite programming) of fixed size, and a nuclear-norm minimization problem. We also present theoretical analysis on the uniqueness and the relaxation gap of our solutions. Extensive experiments on both synthetic and real motion capture data (assuming following the low-order linear combinationmodel) are conducted, which demonstrate that our method indeed outperformsmost of the existing nonrigid factorization methods. This work offers not only new theoretical insight, but also a practical, everyday solution to NRSfM.