Dense Lagrangian motion estimation with occlusions

Ricco, Susanna; Tomasi, Carlo

doi:10.1109/cvpr.2012.6247877

Cited by 29 publications

(38 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, we capitalise on recent advances on multiframe optical flow estimation [31,49,55] and show that the relevant methodologies have matured enough to densely annotate the proposed shapes using either simplistic or even more sophisticated and robust shape representation methods [44]. In particular, in order to build dense correspondences between different shape instances of the same object class, we jointly estimate the optical flow among all the instances by imposing low-rank constrains, an approach that we call Shape Flow.…”

Section: Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

Estimating Correspondences of Deformable Objects “In-the-Wild”

Zhou

Antonakos

Alabort-i-Medina

et al. 2016

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

During the past few years we have witnessed the development of many methodologies for building and fitting Statistical Deformable Models (SDMs). The construction of accurate SDMs requires careful annotation of images with regards to a consistent set of landmarks. However, the manual annotation of a large amount of images is a tedious, laborious and expensive procedure. Furthermore, for several deformable objects, e.g. human body, it is difficult to define a consistent set of landmarks, and, thus, it becomes impossible to train humans in order to accurately annotate a collection of images. Nevertheless, for the majority of objects, it is possible to extract the shape by object segmentation or even by shape drawing. In this paper, we show for the first time, to the best of our knowledge, that it is possible to construct SDMs by putting object shapes in dense correspondence. Such SDMs can be built with much less effort for a large battery of objects. Additionally, we show that, by sampling the dense model, a part-based SDM can be learned with its parts being in correspondence. We employ our framework to develop SDMs of human arms and legs, which can be used for the segmentation of the outline of the human body, as well as to provide better and more consistent annotations for body joints.

show abstract

Section: Contributionsmentioning

confidence: 99%

“…This also defines for every training SVS image a warping function that registers it with the reference SVS image. To establish the dense correspondences robustly, we are inspired by the idea of subspace constraints in the estimation of multiframe optical flow [31,49,55].…”

Section: Constructing Deformable Models With Shape Flowmentioning

confidence: 99%

Estimating Correspondences of Deformable Objects “In-the-Wild”

Zhou

Antonakos

Alabort-i-Medina

et al. 2016

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Our formulation is related to the concept of Lagrangian Motion Estimation (LME) proposed by Ricco and Tomasi [15]. Like them-and several others-we assume that paths belong to a low-dimensional subspace.…”

Section: Summary Of Contributionsmentioning

confidence: 99%

“…(b) Lagrangian motion [15]. Result of transporting all gray levels in the 25-frame marple7 sequence to frame 13 by the image motion computed with our method.…”

Section: Introductionmentioning

confidence: 99%

Video Motion for Every Visible Point

Ricco

Tomasi

2013

2013 IEEE International Conference on Computer Vision

View full text Add to dashboard Cite

Dense motion of image points over many video frames can provide important information about the world. However, occlusions and drift make it impossible to compute long motion paths by merely concatenating optical flow vectors between consecutive frames. Instead, we solve for entire paths directly, and flag the frames in which each is visible. As in previous work, we anchor each path to a unique pixel which guarantees an even spatial distribution of paths. Unlike earlier methods, we allow paths to be anchored in any frame. By explicitly requiring that at least one visible path passes within a small neighborhood of every pixel, we guarantee complete coverage of all visible points in all frames. We achieve state-of-the-art results on real sequences including both rigid and non-rigid motions with significant occlusions.

show abstract

“…Several recent methods solve the multi-frame optical flow problem directly, by implicitly taking into account the rich temporal information that is present in non-rigid scenes [15,36,35,28,30,14]. For example, the long-term 2D trajectories of points on a surface undergoing non-rigid deformation are highly correlated and can be compactly described via a linear combination of a low-rank trajectory basis.…”

Section: Introductionmentioning

confidence: 99%

Face Flow

Snape

Roussos

Panagakis

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

In this paper, we propose a method for the robust and efficient computation of multi-frame optical flow in an expressive sequence of facial images. We formulate a novel energy minimisation problem for establishing dense correspondences between a neutral template and every frame of a sequence. We exploit the highly correlated nature of human expressions by representing dense facial motion using a deformation basis. Furthermore, we exploit the even higher correlation between deformations in a given input sequence by imposing a low-rank prior on the coefficients of the deformation basis, yielding temporally consistent optical flow. Our proposed model-based formulation, in conjunction with the inverse compositional strategy and lowrank matrix optimisation that we adopt, leads to a highly efficient algorithm for calculating facial flow. As experimental evaluation, we show quantitative experiments on a challenging novel benchmark of face sequences, with dense ground truth optical flow provided by motion capture data. We also provide qualitative results on a real sequence displaying fast motion and occlusions. Extensive quantitative and qualitative comparisons demonstrate that the proposed method outperforms state-of-the-art optical flow and dense non-rigid registration techniques, whilst running an order of magnitude faster.

show abstract

Dense Lagrangian motion estimation with occlusions

Cited by 29 publications

References 29 publications

Estimating Correspondences of Deformable Objects “In-the-Wild”

Estimating Correspondences of Deformable Objects “In-the-Wild”

Video Motion for Every Visible Point

Face Flow

Contact Info

Product

Resources

About