A constrained latent variable model

Varol, Aydin; Salzmann, Mathieu; Fua, Pascal; Urtasun, Raquel

doi:10.1109/cvpr.2012.6247934

Cited by 70 publications

(59 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the video, 81 features were tracked along 61 frames showing approximately two periods of bending movement. The training data in this experiment is the cardboard dataset obtained from [39], which is the same as used in the previous evaluations when using cardboard sequence. The results show a comparison of our reconstructed shapes with the results obtained from MP, PTA, KSFM methods.…”

Section: Qualitative Evaluationmentioning

confidence: 99%

“…The testing data used for evaluation include: two articulated face sequences, surprise and talking, both captured using 3D scanner with 3D tracking of 83 facial landmarks and two surface models, cardboard and cloth [39]. This paper does not focus on feature detection and tracking.…”

Section: Rfmentioning

confidence: 99%

“…Forming affinity matrix using random forest technique would efficiently solve such problems as the points are only connected if they are in the same cluster. Figure 4 illustrates the embedding of shapes using diffusion maps and manifold forests from cardboard data [39] together with corresponding representative shapes extracted from 1000 training samples. The embedding results obtained by applying manifold forests seem to be more evenly distributed than points embedded using diffusion maps, especially for the shapes located along the rim of the manifold.…”

Section: Forest Model For Manifold Learningmentioning

confidence: 99%

“…In the experiments described here the 3D points are known and these were projected onto the image sequences under the orthographic camera model and subsequently used as features. Diffusion maps require training process, so training dataset for face sequences were taken from the BU-3DFE [43] and for surface sequences the data were obtained from [39]. All the training data have been rigidly co-registered, and the same testing data have been used with the methods which do not require training.…”

Section: Rfmentioning

confidence: 99%

“…The methods proposed for dealing with this problem can be categorised, by the type of the regularisation technique used, into three major classes: The low-rank shape models [22], shape trajectory approaches [2,14,15], and template-based methods [17,27,39]. In all these methods the regularisation is achieved by reduction in the problem dimensionality.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Robust deformable shape reconstruction from monocular video with manifold forests

Tao

Matuszewski²

2016

Machine Vision and Applications

View full text Add to dashboard Cite

Existing approaches to recover structure of 3D deformable objects and camera motion parameters from an uncalibrated images assume the object's shape could be modelled well by a linear subspace. These methods have been proven effective and well suited when the deformations are relatively small, but fail to reconstruct the objects with relatively large deformations. This paper describes a novel approach for 3D non-rigid shape reconstruction, based on manifold decision forest technique. The use of this technique can be justified by noting that a specific type of shape variations might be governed by only a small number of parameters, and therefore can be well represented in a lowdimensional manifold. The key contributions of this work are the use of random decision forests for the shape manifold learning and robust metric for calculation of the re-projection error. The learned manifold defines constraints imposed on the reconstructed shapes. Due to a nonlinear structure of the learned manifold, this approach is more suitable to deal with large and complex object deformations when compared to the linear constraints. The robust metric is applied to reduce the effect of measurement outliers on the quality of the reconstruction. In many practical applications outliers cannot be completely removed and therefore the use of robust techniques is of particular practical interest. The proposed method is validated on 2D points sequences projected from the 3D motion capture data for ground truth comparison and also on real 2D video sequences. Experiments show that the newly proposed method provides better performance compared to previously proposed ones, including the robustness with respect to measurement noise, missing measurements and outliers present in the data.

show abstract

Section: Qualitative Evaluationmentioning

confidence: 99%

Section: Rfmentioning

confidence: 99%

Section: Forest Model For Manifold Learningmentioning

confidence: 99%

Section: Rfmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Robust deformable shape reconstruction from monocular video with manifold forests

Tao

Matuszewski²

2016

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

Model-free Consensus Maximization for Non-Rigid Shapes

Probst

Chhatkuli

Paudel

et al. 2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

Many computer vision methods use consensus maximization to relate measurements containing outliers with the correct transformation model. In the context of rigid shapes, this is typically done using Random Sampling and Consensus (RANSAC) by estimating an analytical model that agrees with the largest number of measurements (inliers). However, small parameter models may not be always available. In this paper, we formulate the model-free consensus maximization as an Integer Program in a graph using 'rules' on measurements. We then provide a method to solve it optimally using the Branch and Bound (BnB) paradigm. We focus its application on non-rigid shapes, where we apply the method to remove outlier 3D correspondences and achieve performance superior to the state of the art. Our method works with outlier ratio as high as 80%. We further derive a similar formulation for 3D template to image matching, achieving similar or better performance compared to the state of the art.

show abstract

Self-Calibrating Isometric Non-Rigid Structure-from-Motion

Parashar

Bartoli

Pizarro

2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

Non-Rigid Structure-from-Motion (NRSfM) reconstructs a deformable 3D object from the correspondences established between monocular 2D images. Current NRSfM methods lack statistical robustness, which is the ability to cope with correspondence errors. This prevents one to use automatically established correspondences, which are prone to errors, thereby strongly limiting the scope of NRSfM. We propose a three-step automatic pipeline to solve NRSfM robustly by exploiting isometry. Step (i) computes the optical flow from correspondences, step (ii) reconstructs each 3D point's normal vector using multiple reference images and integrates them to form surfaces with the best reference and step (iii) rejects the 3D points that break isometry in their local neighborhood. Importantly, each step is designed to discard or flag erroneous correspondences. Our contributions include the robustification of optical flow by warp estimation, new fast analytic solutions to local normal reconstruction and their robustification, and a new scale-independent measure of 3D local isometric coherence. Experimental results show that our robust NRSfM method consistently outperforms existing methods on both synthetic and real datasets.

show abstract

A constrained latent variable model

Cited by 70 publications

References 29 publications

Robust deformable shape reconstruction from monocular video with manifold forests

Robust deformable shape reconstruction from monocular video with manifold forests

Model-free Consensus Maximization for Non-Rigid Shapes

Self-Calibrating Isometric Non-Rigid Structure-from-Motion

Contact Info

Product

Resources

About