Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspective
This addresses scalability and accuracy issues in 3D reconstruction of deformable objects from images, though it appears incremental as it builds on existing NRSfM approaches.
The paper tackles dense non-rigid structure-from-motion by modeling deformations on a Grassmann manifold, achieving scalability, higher accuracy, and robustness to noise compared to state-of-the-art methods.
This paper addresses the task of dense non-rigid structure-from-motion (NRSfM) using multiple images. State-of-the-art methods to this problem are often hurdled by scalability, expensive computations, and noisy measurements. Further, recent methods to NRSfM usually either assume a small number of sparse feature points or ignore local non-linearities of shape deformations, and thus cannot reliably model complex non-rigid deformations. To address these issues, in this paper, we propose a new approach for dense NRSfM by modeling the problem on a Grassmann manifold. Specifically, we assume the complex non-rigid deformations lie on a union of local linear subspaces both spatially and temporally. This naturally allows for a compact representation of the complex non-rigid deformation over frames. We provide experimental results on several synthetic and real benchmark datasets. The procured results clearly demonstrate that our method, apart from being scalable and more accurate than state-of-the-art methods, is also more robust to noise and generalizes to highly non-linear deformations.