Organic Priors in Non-Rigid Structure from Motion

TL;DR

This paper introduces a novel method leveraging organic priors inherent in NRSfM matrix factorization to improve 3D shape and motion recovery under orthographic projection, outperforming prior-free methods.

Contribution

It proposes a practical approach that exploits intrinsic priors in NRSfM matrices, revealing their independence from camera motion and shape deformation, and introduces single rotation averaging for enhanced results.

Findings

Outperforms prior-free NRSfM methods significantly

Shows organic priors are independent of camera motion and shape deformation

First to demonstrate benefits of single rotation averaging in NRSfM

Abstract

This paper advocates the use of organic priors in classical non-rigid structure from motion (NRSfM). By organic priors, we mean invaluable intermediate prior information intrinsic to the NRSfM matrix factorization theory. It is shown that such priors reside in the factorized matrices, and quite surprisingly, existing methods generally disregard them. The paper's main contribution is to put forward a simple, methodical, and practical method that can effectively exploit such organic priors to solve NRSfM. The proposed method does not make assumptions other than the popular one on the low-rank shape and offers a reliable solution to NRSfM under orthographic projection. Our work reveals that the accessibility of organic priors is independent of the camera motion and shape deformation type. Besides that, the paper provides insights into the NRSfM factorization -- both in terms of shape and motion -- and is the first approach to show the benefit of single rotation averaging for NRSfM. Furthermore, we outline how to effectively recover motion and non-rigid 3D shape using the proposed organic prior based approach and demonstrate results that outperform prior-free NRSfM performance by a significant margin. Finally, we present the benefits of our method via extensive experiments and evaluations on several benchmark datasets.