A Closed-Form Solution to Local Non-Rigid Structure-from-Motion
This work addresses the problem of efficiently and accurately reconstructing 3D non-rigid shapes from 2D images, which is important for computer vision and graphics applications, by providing a more robust and faster solution.
This paper presents a new system of equations for Non-Rigid Structure-from-Motion (NRSfM) that allows for the closed-form computation of surface normals from local, differential constraints between image pairs. The proposed method yields significantly more accurate reconstructions and is faster than state-of-the-art methods.
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.