A Closed-Form Solution to Local Non-Rigid Structure-from-Motion

TL;DR

This paper introduces a closed-form solution for local non-rigid structure-from-motion that simplifies computation, improves accuracy, and assesses the reliability of surface normal estimates.

Contribution

The authors derive a new system of equations with closed-form solutions for local surface normals in NRSfM, addressing degeneracies and enabling reliability assessment.

Findings

More accurate reconstructions than state-of-the-art methods

Faster computation due to closed-form solutions

Ability to discard unreliable normal estimates

Abstract

A recent trend in Non-Rigid Structure-from-Motion (NRSfM) is to express local, differential constraints between pairs of images, from which the surface normal at any point can be obtained by solving a system of polynomial equations. The systems of equations derived in previous work, however, are of high degree, having up to five real solutions, thus requiring a computationally expensive strategy to select a unique solution. Furthermore, they suffer from degeneracies that make the resulting estimates unreliable, without any mechanism to identify this situation. In this paper, we show that, under widely applicable assumptions, we can derive a new system of equation in terms of the surface normals whose two solutions can be obtained in closed-form and can easily be disambiguated locally. Our formalism further allows us to assess how reliable the estimated local normals are and, hence, to discard them if they are not. Our experiments show that our reconstructions, obtained from two or more views, are significantly more accurate than those of state-of-the-art methods, while also being faster.