Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspective
arXiv:1803.00233
Abstract
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.
arXiv comment10 pages, 7 figure, 4 tables. Accepted for publication in Conference on Computer Vision and Pattern Recognition (CVPR), 2018, typos fixed and acknowledgement added
References in corpus (4)
- Robust Recovery of Subspace Structures by Low-Rank Representation
- Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames
- Low Rank Representation on Grassmann Manifolds: An Extrinsic Perspective
- Dense Non-rigid Structure-from-Motion Made Easy - A Spatial-Temporal Smoothness based Solution