Results 1  10
of
25
Markov Random Field Modeling, Inference & Learning in Computer Vision & Image Understanding: A Survey
, 2013
"... ..."
Fast Joint Estimation of Silhouettes and Dense 3D Geometry from Multiple Images " Ieee transactionson pattern analysis and machine intelligence ,Digital Object Indentifier .1109/TPAMI.2011.150 0162
, 2011
"... Abstract—We propose a probabilistic formulation of joint silhouette extraction and 3D reconstruction given a series of calibrated 2D images. Instead of segmenting each image separately in order to construct a 3D surface consistent with the estimated silhouettes, we compute the most probable 3D shape ..."
Abstract

Cited by 12 (1 self)
 Add to MetaCart
(Show Context)
Abstract—We propose a probabilistic formulation of joint silhouette extraction and 3D reconstruction given a series of calibrated 2D images. Instead of segmenting each image separately in order to construct a 3D surface consistent with the estimated silhouettes, we compute the most probable 3D shape that gives rise to the observed color information. The probabilistic framework, based on Bayesian inference, enables robust 3D reconstruction by optimally taking into account the contribution of all views. We solve the arising maximum a posteriori shape inference in a globally optimal manner by convex relaxation techniques in a spatially continuous representation. For an interactively provided user input in the form of scribbles specifying foreground and background regions, we build corresponding color distributions as multivariate Gaussians and find a volume occupancy that best fits to this data in a variational sense. Compared to classical methods for silhouettebased multiview reconstruction, the proposed approach does not depend on initialization and enjoys significant resilience to violations of the model assumptions due to background clutter, specular reflections, and camera sensor perturbations. In experiments on several realworld data sets, we show that exploiting a silhouette coherency criterion in a multiview setting allows for dramatic improvements of silhouette quality over independent 2D segmentations without any significant increase of computational efforts. This results in more accurate visual hull estimation, needed by a multitude of imagebased modeling approaches. We made use of recent advances in parallel computing with a GPU implementation of the proposed method generating reconstructions on volume grids of more than 20 million voxels in up to 4.41 seconds. Index Terms—Shape from silhouettes, interactive segmentation, convex optimization. Ç 1
Minimizing Energies with Hierarchical Costs
 INTERNATIONAL JOURNAL OF COMPUTER VISION
, 2012
"... Computer vision is full of problems elegantly expressed in terms of energy minimization. We characterize a class of energies with hierarchical costs and propose a novel hierarchical fusion algorithm. Hierarchical costs are natural for modeling an array of difficult problems. For example, in semantic ..."
Abstract

Cited by 10 (1 self)
 Add to MetaCart
(Show Context)
Computer vision is full of problems elegantly expressed in terms of energy minimization. We characterize a class of energies with hierarchical costs and propose a novel hierarchical fusion algorithm. Hierarchical costs are natural for modeling an array of difficult problems. For example, in semantic segmentation one could rule out unlikely object combinations via hierarchical context. In geometric model estimation, one could penalize the number of unique model families in a solution, not just the number of models—a kind of hierarchical MDL criterion. Hierarchical fusion uses the wellknown αexpansion algorithm as a subroutine, and offers a much better approximation bound in important cases.
Generalized Roof Duality for PseudoBoolean Optimization
"... The number of applications in computer vision that model higherorder interactions has exploded over the last few years. The standard technique for solving such problems is to reduce the higherorder objective function to a quadratic pseudoboolean function, and then use roof duality for obtaining a ..."
Abstract

Cited by 7 (1 self)
 Add to MetaCart
(Show Context)
The number of applications in computer vision that model higherorder interactions has exploded over the last few years. The standard technique for solving such problems is to reduce the higherorder objective function to a quadratic pseudoboolean function, and then use roof duality for obtaining a lower bound. Roof duality works by constructing the tightest possible lowerbounding submodular function, and instead of optimizing the original objective function, the relaxation is minimized. We generalize this idea to polynomials of higher degree, where quadratic roof duality appears as a special case. Optimal relaxations are defined to be the ones that give the maximum lower bound. We demonstrate that important properties such as persistency still hold and how the relaxations can be efficiently constructed for general cubic and quartic pseudoboolean functions. From a practical point of view, we show that our relaxations perform better than stateoftheart for a wide range of problems, both in terms of lower bounds and in the number of assigned variables. 1.
A distributed mincut/maxflow algorithm combining path augmentation and pushrelabel
 IN PROCEEDINGS OF THE 8TH INTERNATIONAL CONFERENCE ON ENERGY MINIMIZATION METHODS IN COMPUTER VISION AND PATTERN RECOGNITION (EMMCVPR), LECTURE NOTES IN COMPUTER SCIENCE
, 2011
"... ..."
Image Labeling on a Network: Using SocialNetwork Metadata for Image
"... Classification ..."
(Show Context)
Optimization for MultiRegion Segmentation of Cardiac MRI
"... Abstract. We introduce a new multiregion model for simultaneous segmentation of the left and right ventricles, myocardium and the left ventricular papillary muscles in MRI. The model enforces geometric constraints such as inclusion and exclusion between the regions, which makes it possible to corre ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
(Show Context)
Abstract. We introduce a new multiregion model for simultaneous segmentation of the left and right ventricles, myocardium and the left ventricular papillary muscles in MRI. The model enforces geometric constraints such as inclusion and exclusion between the regions, which makes it possible to correctly segment different regions even though the intensity distributions are identical. We efficiently optimize the model using Lagrangian duality which is faster and more memory efficient than current state of the art. As the optimization is based on global techniques, the resulting segmentations are independent of initialization. We evaluate our approach on two benchmarks with competitive results. 1
Nearoptimal anomaly detection in graphs using Lovász extended scan statistic
, 2013
"... ..."
(Show Context)
Convexity in ImageBased 3D Surface Reconstruction
, 2011
"... The real voyage of discovery consists not in seeking new landscapes, but in having new eyes. Marcel Proust (18711922) As the title of the current thesis suggests, convex modeling will play a central role throughout the work. Yet, convexity is utilized not as a construct to give a scientific form to ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
The real voyage of discovery consists not in seeking new landscapes, but in having new eyes. Marcel Proust (18711922) As the title of the current thesis suggests, convex modeling will play a central role throughout the work. Yet, convexity is utilized not as a construct to give a scientific form to the thesis. I will try to convince the skeptic readers that, along with mathematical elegance, it provides the capabilities to build robust and accurate approaches of high practical value. One could argue that focusing on convex formulations limits the sight and does not allow to explore the whole potential of the application. In particular, it is debatable if the starting point of developing novel methods should be the optimization or the structure of the model. Accordingly, one can distinguish between two different research philosophies. While I was following “optimizationoriented ” principles, there are of course many alternative approaches which may be equally valid. As always in research, there is not just one way to reach a goal. Although special attention was attached to the intelligibility of the thesis, the reader needs some basic knowledge of analysis, variational calculus and epipolar geometry to understand