A simple prior-free method for non-rigid structure-from-motion factorization

@inproceedings{Dai2012ASP,
  title={A simple prior-free method for non-rigid structure-from-motion factorization},
  author={Yuchao Dai and Hongdong Li and Mingyi He},
  booktitle={CVPR},
  year={2012}
}
This paper proposes a simple “prior-free” method for solving non-rigid structure-from-motion factorization problems. Other than using the basic low-rank condition, our method does not assume any extra prior knowledge about the nonrigid scene or about the camera motions. Yet, it runs reliably, produces optimal result, and does not suffer from the inherent basis-ambiguity issue which plagued many conventional nonrigid factorization techniques. Our method is easy to implement, which involves… 
A Simple Prior-Free Method for Non-rigid Structure-from-Motion Factorization
TLDR
This paper proposes a simple “prior-free” method for solving the non-rigid structure-from-motion (NRSfM) factorization problem, which involves solving a very small SDP of fixed size, and a nuclear-norm minimization problem.
A Simple Prior-Free Method for Non-rigid Structure-from-Motion Factorization : Revisited
A simple prior free factorization algorithm[8] is quite often cited work in the field of Non-Rigid Structure from Motion (NRSfM). The benefit of this work lies in its simplicity of implementation,
NON-rigid structure from motion via sparse self-expressive representation
  • Junjie Hu, T. Aoki
  • Computer Science
    2017 IEEE International Conference on Image Processing (ICIP)
  • 2017
TLDR
This paper presents a self-expressive method that models 3D shapes with a sparse combination of other3D shapes from the same structure that doesn't need the rank to be predefined.
A scalable, efficient, and accurate solution to non-rigid structure from motion
A Convex Approach for Non-rigid Structure from Motion Via Sparse Representation
TLDR
A convex solution for simultaneously recovering 3D non-rigid structures and camera motions from 2D image sequences based on sparse representation is presented and achieves state-of-the-art reconstruction performance on CMU benchmark dataset.
Dense Batch Non-Rigid Structure from Motion in a Second
TLDR
The modification results in an efficient single-core CPU implementation enabling dense factorisations of long image sequences with tens of thousands of points into camera pose and non-rigid shape in seconds, i.e., at least two orders of magnitude faster than the runtimes reported in the literature so far.
Recovering complex non-rigid 3D structures from monocular images by union of nonlinear subspaces
TLDR
The nonlinear low-rank representation as a regularizer to the objective function for NRSfM is introduced and it is shown that it can be solved by alternating direction multiplier method (ADMM), and the method yields more accurate reconstruction and more reasonable clustering results than state-of-the-art methods.
Latent-Smoothness Nonrigid Structure From Motion by Revisiting Multilinear Factorization
TLDR
The MLF scheme for improving factorization accuracy is reinvestigated, and an MLF method with the only low-rank prior for NRSFM in the presence of missing data is proposed, and a regularized factorization method is proposed by integrating MLF with the explored latent-smoothness prior for further pursuing better performances.
Dense Variational Reconstruction of Non-rigid Surfaces from Monocular Video
TLDR
This paper offers the first variational approach to the problem of dense 3D reconstruction of non-rigid surfaces from a monocular video sequence and reconstructs highly deforming smooth surfaces densely and accurately directly from video, without the need for any prior models or shape templates.
Sequential factorization for nonrigid structure from motion via LBFGS
  • Qiulei Dong, Hao Hu
  • Computer Science
    2016 23rd International Conference on Pattern Recognition (ICPR)
  • 2016
TLDR
This work proposes a novel sequential factorization method without extra priors other than the basis low-rank prior, consisting of a motion estimation module and a 3D shape recovery module, which can achieve an effective tradeoff between estimation accuracy and computational speed.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 58 REFERENCES
Implicit Non-Rigid Structure-from-Motion with Priors
TLDR
An algorithm for achieving a Maximum A Posteriori (map) solution is proposed and it is shown experimentally that the map-solution generalizes far better than the prior-free Maximum Likelihood (ml) solution.
A Unified View on Deformable Shape Factorizations
TLDR
This paper shows that these NRSfM factorization approaches are most naturally modeled with tensor algebra and can be extended to the case of a camera network where multiple static affine cameras observe the same deforming and moving non-rigid object.
Element-Wise Factorization for N-View Projective Reconstruction
TLDR
This paper recasts the problem as matrix factorization as element-wise factorization, leading to a convenient and efficient semi-definite program formulation, and presents an optimal solution to projective factorization for structure and motion, based on the same principle of low-rank factorization.
Linear embeddings in non-rigid structure from motion
TLDR
This paper proposes a method to recover the embedding of the possible shapes assumed by a deforming nonrigid object by comparing triplets of frames from an orthographic video sequence and finds it to perform better than current state of the art.
Projective Multiview Structure and Motion from Element-Wise Factorization
TLDR
The projective SfM problem is formulated as a novel and original element-wise factorization (i.e., Hadamard factorization) problem, as opposed to the conventional matrix factorization, and this formulation is able to solve the projective depths, structure, and camera motions simultaneously by convex optimization.
Factorization for non-rigid and articulated structure using metric projections
TLDR
An alternating least-squares approach associated with a globally optimal projection step onto the manifold of metric constraints for recovering the 3D shape and motion of deformable and articulated objects purely from uncalibrated 2D image measurements is proposed.
Multi-view structure computation without explicitly estimating motion
  • Hongdong Li
  • Computer Science
    2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
TLDR
A novel scheme which bypasses the motion-estimation step, and goes directly to structure computation step is presented, demonstrating that such a scheme is not only theoretically possible, but also technically feasible and effective.
Kernel non-rigid structure from motion
TLDR
This work demonstrates how the kernel trick can be applied in standard NRSFM and model complex, deformable 3D shapes as the outputs of a non-linear mapping whose inputs are points within a low-dimensional shape space.
Non-rigid structure from motion with complementary rank-3 spaces
TLDR
This paper proposes a new algorithm that revises the standard matrix factorization approach in NR-SFM, providing improved results on high-frequency deformations of both articulated and simpler deformable shapes.
A factorization approach to structure from motion with shape priors
  • A. D. Bue
  • Mathematics
    2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
TLDR
The proposed method computes a closed-form affine fit which mixes the information from the data and the 3D prior on the shape structure, which is general in regards to different classes of objects treated: rigid, articulated and deformable.
...
1
2
3
4
5
...