Complex Non-rigid Motion 3D Reconstruction by Union of Subspaces

Zhu, Yingying; Huang, Dong; Torre, Fernando De la; Lucey, Simon

doi:10.1109/cvpr.2014.200

Cited by 131 publications

(158 citation statements)

References 9 publications

Supporting

Mentioning

158

Contrasting

Order By: Relevance

“…Later they proposed a method focusing on a globally linear manifold and use shape embedding as initialisation [25]. Similarly, the work in [45] attempts to learn the 3D reconstruction of human motion with an assumption that human poses lie in a union of subspaces.…”

Section: Introductionmentioning

confidence: 99%

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: Introductionmentioning

confidence: 99%

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

“…Subspace clustering can be a useful tool in computer vision, because there are many types of data that can be wellrepresented by a low-dimensional structure such as face, motion, video segments, etc. Accordingly, there have been many successful applications of subspace clustering [4,31].…”

Section: Introductionmentioning

confidence: 99%

Membership representation for detecting block-diagonal structure in low-rank or sparse subspace clustering

Lee

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

“…We can also explore some novel applications for the proposed strategy such as super resolution [59], 3D reconstruction [127,128], or anomaly detection in surveillance systems [116]. Here we can use attributes of low-resolution images as the query to collect the high-resolution images which have similar parts to that, then use the patches of the high-resolution images as sources to approximate the patches of low-resolution images and reconstruct the high-resolution images.…”

Section: Discussionmentioning

confidence: 99%

“…Another interesting future direction is to find the smallest set of attributes by adding an additional regularisation term in the objective function. We can also explore some novel applications for the proposed strategy such as super resolution [59], 3D reconstruction [127,128], or anomaly detection in surveillance systems [116].…”

Section: Future Workmentioning

confidence: 99%

“…A more large-scale user study using AMT on other datasets may be more desirable since human evaluation also plays an important part in further validation. Some other directions could be to investigate the influence of the degenerated or low-resolution image [59] on the attribute meaningfulness evaluation, or to evaluate the potential attributes for 3D reconstructed image sequences [127]. Furthermore, The same meaningful subspace approximation idea can be extended using a deep learning framework.…”

Section: Future Workmentioning

confidence: 99%

See 1 more Smart Citation

Discovering visual attributes from image and video data

Liu¹

View full text Add to dashboard Cite

Visual attributes have recently attracted great attention from the computer vision community.Their advantages include being: (1) shared across classes, (2) human understandable, and (3) machine computable. Despite these positives, the attribute features in current works are not discriminative enough to be considered as strong features for traditional classification tasks or novel applications. This problem hinders their broad usage. There are several works that primarily focus on increasing the discriminative power of visual attributes. Unfortunately, in most cases, the feature descriptors become hard to understand (i.e., not meaningful); thus, reducing these attribute features into being merely traditional low-level image/video feature descriptors. Furthermore, the discriminative power property and meaningful property are not independent. Some discriminative attributes could be meaningful and vice-versa. For example, the attribute "has hooves" is discriminative for distinguishing between dogs and sheep but the attribute "has four legs" is not. On the other hand, there is significant attention being given to the development of automatic attribute discovery approaches. These approaches focus on automatically discovering potentially meaningful attributes from data without the need for manual labelling. Although it is suggested that the discovered attributes are quite discriminative and meaningful, it is not entirely clear if they are truly meaningful. Quantitative and automatic evaluation methods to determine attribute meaningfulness are desirable in this case, since manual examination is both tedious and time-consuming. Research on this topic can start to shed light on how to automatically and effectively discover meaningful visual attributes without the huge cost of manual labelling.The following research directions have not previously been extensively explored: (1) current works fail to address the problem of finding discriminative and meaningful attributes without involving human effort, and (2) there is no existing way to measure the meaning of discriminative attributes without involving human labelling effort. To that end, this research aims to devise visual attributebased methods for traditional classification tasks and novel applications, including the attribute meaningfulness measurement, by dealing with these two shortcomings. In particular, this thesis addresses the following aspects: (1) automatic discovery of discriminative attributes from a set of meaningful attributes applied to zero-shot learning problems; (2) discovery of meaningful attributes by exploring ways to automatically quantify attribute meaningfulness; the proposed techniques are applied and tested on video keyword generation for video surveillance data, and (3) discovering meaningful and discriminative attributes in fully unsupervised scenarios via multi-graph clustering techniques. The main contribution of this thesis lies in the proposition of the method quantitatively evaluating the meaningfulness of automatic discovered attr...

show abstract

Complex Non-rigid Motion 3D Reconstruction by Union of Subspaces

Cited by 131 publications

References 9 publications

Robust deformable shape reconstruction from monocular video with manifold forests

Robust deformable shape reconstruction from monocular video with manifold forests

Membership representation for detecting block-diagonal structure in low-rank or sparse subspace clustering

Discovering visual attributes from image and video data

Contact Info

Product

Resources

About