Convex Optimization for Deformable Surface 3-D Tracking

Salzmann, Matthieu; Hartley, Richard; Fua, Pascal

doi:10.1109/iccv.2007.4409031

Cited by 100 publications

(106 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use several datasets that have been previously introduced in [2,8,20,11]. We start by providing details about the construction of the neighbourhood system and the computation of the error measures.…”

Section: Methodsmentioning

confidence: 99%

Soft Inextensibility Constraints for Template-Free Non-rigid Reconstruction

Vicente

Agapito

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

Abstract. In this paper, we exploit an inextensibility prior as a way to better constrain the highly ambiguous problem of non-rigid reconstruction from monocular views. While this widely applicable prior has been used before combined with the strong assumption of a known 3D-template, our work achieves template-free reconstruction using only inextensibility constraints. We show how to formulate an energy function that includes soft inextensibility constraints and rely on existing discrete optimisation methods to minimise it. Our method has all of the following advantages: (i) it can be applied to two tasks that have been so far considered independently -template based reconstruction and non-rigid structure from motion -producing comparable or better results than the state-of-the art methods; (ii) it can perform template-free reconstruction from as few as two images; and (iii) it does not require post-processing stitching or surface smoothing.

show abstract

Section: Methodsmentioning

confidence: 99%

Soft Inextensibility Constraints for Template-Free Non-rigid Reconstruction

Vicente

Agapito

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

show abstract

“…21 Estimated 2D mesh on the video sequence of deforming cloth using our approach. The dataset in the first and the last row come from [33], while the dataset in the middle row comes from [25]. Using warp-back strategies.…”

Section: Conceptual Comparisons With Previous Methodsmentioning

confidence: 99%

Globally Optimal Estimation of Nonrigid Image Distortion

Tian

Narasimhan

2011

Int J Comput Vis

View full text Add to dashboard Cite

Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformation field that warps a distorted image back to its undistorted template. Generative approaches based on parameter optimization such as Lucas-Kanade can get trapped within local minima. On the other hand, discriminative approaches like nearestneighbor require a large number of training samples that grows exponentially with respect to the dimension of the parameter space, and polynomially with the desired accuracy 1/ . In this work, we develop a novel data-driven iterative algorithm that combines the best of both generative and discriminative approaches. For this, we introduce the notion of a "pull-back" operation that enables us to predict the parameters of the test image using training samples that are not in its neighborhood (not -close) in the parameter space. We prove that our algorithm converges to the global optimum using a significantly lower number of training samples that grows only logarithmically with the desired accuracy. We analyze the behavior of our algorithm extensively using synthetic data and demonstrate successful results on experiments with complex deformations due to water and clothing.

show abstract

“…. and pixel-based data term (14) 0.10 1.60 Figure 6: Evolution of the Free-Form Deformation control points average error relative to the tracking based method [6]. Our method is evaluated with the bending energy prior , adding the shrinker term for better robustness to self-occlusions, and the pixel-based data term for better accuracy .…”

Section: Quantitative Evaluation On a Real Sequencementioning

confidence: 99%

Combining Features and Intensity for Wide-Baseline Non-Rigid Surface Registration

Braux-Zin¹,

Dupont²,

Bartoli³

2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

Non-rigid surface registration consists in estimating the deformation of a known flat surface, usually by fitting a warp such as a Thin-Plate Spline or a Free-Form Deformation. Common techniques are split in two categories: (1) pixel-based surface tracking where important deformations can be estimated over a video sequence as long as the frame to frame steps are small and (2) wide-baseline feature-based registration, able to directly handle large deformations at the cost of reduced accuracy. We introduce a new direct data term robustly merging feature and pixel-based costs in a pyramidal variational approach. By using a robust estimator we achieve an implicit optimal filtering of features and automatic balancing between the two terms.

show abstract

Convex Optimization for Deformable Surface 3-D Tracking

Abstract: 3-D shape recovery of non-rigid surfaces from 3-D to 2-D correspondences is an under

Cited by 100 publications

References 15 publications

Soft Inextensibility Constraints for Template-Free Non-rigid Reconstruction

Soft Inextensibility Constraints for Template-Free Non-rigid Reconstruction

Globally Optimal Estimation of Nonrigid Image Distortion

Combining Features and Intensity for Wide-Baseline Non-Rigid Surface Registration

Contact Info

Product

Resources

About