Multilinear pose and body shape estimation of dressed subjects from image sets

Hasler, Nils; Ackermann, Hanno; Rosenhahn, Bodo; Thormählen, Thorsten; Seidel, Hans‐Peter

doi:10.1109/cvpr.2010.5539853

Cited by 108 publications

(77 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed solution can be used to initialize a bundle adjustment. Although structure and motion estimation was presented as application the proposed algorithm is general and can be applied to any PCA problem [13,20,12,19,2].…”

Section: Resultsmentioning

confidence: 99%

“…(3) is not entirely suitable for 3D-reconstruction. Nonetheless, the L 2 metric is quite general and can be directly applied to many other problems [13,20,12]. For SfM, we therefore like to interpret the used error as an approximation of the prefered metric.…”

Section: Real World Applicationsmentioning

confidence: 99%

“…It is used, for instance, for computation of eigenfaces [13], image matching [20], pose and shape estimation [12], rigid structure and motion (SfM) estimation [19] or nonrigid SfM [2]. Singular value decomposition (SVD) is often used to compute a PCA.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multilinear Model Estimation with L 2-Regularization

Schmidt

Ackermann

Rosenhahn

2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Many challenging computer vision problems can be formulated as a multilinear model. Classical methods like principal component analysis use singular value decomposition to infer model parameters. Although it can solve a given problem easily if all measurements are known this prerequisite is usually violated for computer vision applications. In the current work, a standard tool to estimate singular vectors under incomplete data is reformulated as an energy minimization problem. This admits for a simple and fast gradient descent optimization with guaranteed convergence. Furthermore, the energy function is generalized by introducing an L 2 -regularization on the parameter space. We show a quantitative and qualitative evaluation of the proposed approach on an application from structure-from-motion using synthetic and real image data, and compare it with other works.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Real World Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Multilinear Model Estimation with L 2-Regularization

Schmidt

Ackermann

Rosenhahn

2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Brubaker et al [16] use a simple lower-body model based on physical walking movement called Antropomorphic Walker, proposed by Kuo [17]. Hasler et al [18] propose a pose estimation algorithm which performs on mono and multiple uncalibrated cameras. Unfortunately, single color cameras inherently provide poor information, due to information loss originated from perspective projection.…”

Section: Related Workmentioning

confidence: 99%

Detecting end-effectors on 2.5D data using geometric deformable models: Application to human pose estimation

Suau

Ruiz-Hidalgo

Casas

2013

Computer Vision and Image Understanding

View full text Add to dashboard Cite

End-effectors are usually related to the location of limbs, and their reliable detection enables robust body tracking as well as accurate pose estimation. Recent innovation in depth cameras has re-stated the pose estimation problem. We focus on the information provided by these sensors, for which we borrow the name 2.5D data from the Graphics community. In this paper we propose a human pose estimation algorithm based on topological propagation. Geometric Deformable Models are used to carry out such propagation, implemented according to the Narrow Band Level Set approach. A variant of the latter method is proposed, including a density restriction which helps preserving the topological properties of the object under analysis. Principal end-effectors are extracted from a directed graph weighted with geodesic distances, also providing a skeletal-like structure describing human pose. An evaluation against reference methods is performed with promising results. The proposed solution allows a frame-wise end-effector detection, with no temporal tracking involved, which may be generalized to the tracking of other objects beyond human body.

show abstract

“…To recover more detailed non-rigid motion of people and clothing from multiple view reconstructions Aguiar et al [1] employ an initial high-resolution 3D body scan and use an implicit volumetric parameterisation of the shape to constrain the deformation. Recent approaches [15,2,9] have employed learnt statistical models of human shape and pose to recover both non-rigid shape and motion from monocular image sequences. Stoll et al [18] combine non-rigid surface tracking and a high-resolution 3D body scan with statistical body models and physics-based cloth simulation to estimate and reproduce highly realistic nonrigid cloth dynamics.…”

Section: Related Workmentioning

confidence: 99%

Global temporal registration of multiple non-rigid surface sequences

2011

View full text Add to dashboard Cite

In this paper we consider the problem of aligning multiple non-rigid surface mesh sequences into a single temporally consistent representation of the shape and motion. A global alignment graph structure is introduced which uses shape similarity to identify frames for inter-sequence registration. Graph optimisation is performed to minimise the total non-rigid deformation required to register the input sequences into a common structure. The resulting global alignment ensures that all input sequences are resampled with a common mesh structure which preserves the shape and temporal correspondence. Results demonstrate temporally consistent representation of several public databases of mesh sequences for multiple people performing a variety of motions with loose clothing and hair.

show abstract

Multilinear pose and body shape estimation of dressed subjects from image sets

Cited by 108 publications

References 21 publications

Multilinear Model Estimation with L 2-Regularization

Multilinear Model Estimation with L 2-Regularization

Detecting end-effectors on 2.5D data using geometric deformable models: Application to human pose estimation

Global temporal registration of multiple non-rigid surface sequences

Contact Info

Product

Resources

About