Organic Priors in Non-Rigid Structure from Motion
- URL: http://arxiv.org/abs/2207.06262v2
- Date: Thu, 14 Jul 2022 17:45:34 GMT
- Title: Organic Priors in Non-Rigid Structure from Motion
- Authors: Suryansh Kumar, Luc Van Gool
- Abstract summary: This paper advocates the use of organic priors in classical non-rigid structure from motion (NRSfM)
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.
- Score: 102.41675461817177
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Coseparable Nonnegative Tensor Factorization With T-CUR Decomposition [2.013220890731494]
Nonnegative Matrix Factorization (NMF) is an important unsupervised learning method to extract meaningful features from data.
In this work, we provide an alternating selection method to select the coseparable core.
The results demonstrate the efficiency of coseparable NTF when compared to coseparable NMF.
arXiv Detail & Related papers (2024-01-30T09:22:37Z) - Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization [102.92240148504774]
We study a principled finetuning paradigm -- Orthogonal Finetuning (OFT) -- for downstream task adaptation.
Despite demonstrating good generalizability, OFT still uses a fairly large number of trainable parameters.
We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT)
arXiv Detail & Related papers (2023-11-10T18:59:54Z) - Large-Scale OD Matrix Estimation with A Deep Learning Method [70.78575952309023]
The proposed method integrates deep learning and numerical optimization algorithms to infer matrix structure and guide numerical optimization.
We conducted tests to demonstrate the good generalization performance of our method on a large-scale synthetic dataset.
arXiv Detail & Related papers (2023-10-09T14:30:06Z) - Supervised Class-pairwise NMF for Data Representation and Classification [2.7320863258816512]
Non-negative Matrix factorization (NMF) based methods add new terms to the cost function to adapt the model to specific tasks.
NMF method adopts unsupervised approaches to estimate the factorizing matrices.
arXiv Detail & Related papers (2022-09-28T04:33:03Z) - Finding Rule-Interpretable Non-Negative Data Representation [2.817412580574242]
We present a version of the NMF approach that merges rule-based descriptions with advantages of part-based representation.
The proposed approach provides numerous advantages in tasks such as focused embedding or performing supervised multi-label NMF.
arXiv Detail & Related papers (2022-06-03T10:20:46Z) - Initialization for Nonnegative Matrix Factorization: a Comprehensive
Review [0.0]
Non-negative factorization (NMF) has become a popular method for representing meaningful data by extracting a non-negative basis from an non-negative data matrix.
Some numerical results to illustrate the performance of each method are presented.
arXiv Detail & Related papers (2021-09-08T18:49:41Z) - Feature Weighted Non-negative Matrix Factorization [92.45013716097753]
We propose the Feature weighted Non-negative Matrix Factorization (FNMF) in this paper.
FNMF learns the weights of features adaptively according to their importances.
It can be solved efficiently with the suggested optimization algorithm.
arXiv Detail & Related papers (2021-03-24T21:17:17Z) - Revisiting Initialization of Neural Networks [72.24615341588846]
We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix.
Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
arXiv Detail & Related papers (2020-04-20T18:12:56Z) - Augmentation of the Reconstruction Performance of Fuzzy C-Means with an
Optimized Fuzzification Factor Vector [99.19847674810079]
Fuzzy C-Means (FCM) is one of the most frequently used methods to construct information granules.
In this paper, we augment the FCM-based degranulation mechanism by introducing a vector of fuzzification factors.
Experiments completed for both synthetic and publicly available datasets show that the proposed approach outperforms the generic data reconstruction approach.
arXiv Detail & Related papers (2020-04-13T04:17:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.