Results 1  10
of
110
Feature Correspondence via Graph Matching: Models and Global Optimization
"... Abstract. In this paper we present a new approach for establishing correspondences between sparse image features related by an unknown nonrigid mapping and corrupted by clutter and occlusion, such as points extracted from a pair of images containing a human figure in distinct poses. We formulate th ..."
Abstract

Cited by 117 (1 self)
 Add to MetaCart
(Show Context)
Abstract. In this paper we present a new approach for establishing correspondences between sparse image features related by an unknown nonrigid mapping and corrupted by clutter and occlusion, such as points extracted from a pair of images containing a human figure in distinct poses. We formulate this matching task as an energy minimization problem by defining a complex objective function of the appearance and the spatial arrangement of the features. Optimization of this energy is an instance of graph matching, which is in general a NPhard problem. We describe a novel graph matching optimization technique, which we refer to as dual decomposition (DD), and demonstrate on a variety of examples that this method outperforms existing graph matching algorithms. In the majority of our examples DD is able to find the global minimum within a minute. The ability to globally optimize the objective allows us to accurately learn the parameters of our matching model from training examples. We show on several matching tasks that our learned model yields results superior to those of stateoftheart methods. 1
MRF energy minimization and beyond via dual decomposition
 IN: IEEE PAMI. (2011
"... This paper introduces a new rigorous theoretical framework to address discrete MRFbased optimization in computer vision. Such a framework exploits the powerful technique of Dual Decomposition. It is based on a projected subgradient scheme that attempts to solve an MRF optimization problem by first ..."
Abstract

Cited by 107 (10 self)
 Add to MetaCart
(Show Context)
This paper introduces a new rigorous theoretical framework to address discrete MRFbased optimization in computer vision. Such a framework exploits the powerful technique of Dual Decomposition. It is based on a projected subgradient scheme that attempts to solve an MRF optimization problem by first decomposing it into a set of appropriately chosen subproblems and then combining their solutions in a principled way. In order to determine the limits of this method, we analyze the conditions that these subproblems have to satisfy and we demonstrate the extreme generality and flexibility of such an approach. We thus show that, by appropriately choosing what subproblems to use, one can design novel and very powerful MRF optimization algorithms. For instance, in this manner we are able to derive algorithms that: 1) generalize and extend stateoftheart messagepassing methods, 2) optimize very tight LPrelaxations to MRF optimization, 3) and take full advantage of the special structure that may exist in particular MRFs, allowing the use of efficient inference techniques such as, e.g, graphcut based methods. Theoretical analysis on the bounds related with the different algorithms derived from our framework and experimental results/comparisons using synthetic and real data for a variety of tasks in computer vision demonstrate the extreme potentials of our approach.
Graph cut based image segmentation with connectivity priors
, 2008
"... Graph cut is a popular technique for interactive image segmentation. However, it has certain shortcomings. In particular, graph cut has problems with segmenting thin elongated objects due to the “shrinking bias”. To overcome this problem, we propose to impose an additional connectivity prior, which ..."
Abstract

Cited by 102 (8 self)
 Add to MetaCart
(Show Context)
Graph cut is a popular technique for interactive image segmentation. However, it has certain shortcomings. In particular, graph cut has problems with segmenting thin elongated objects due to the “shrinking bias”. To overcome this problem, we propose to impose an additional connectivity prior, which is a very natural assumption about objects. We formulate several versions of the connectivity constraint and show that the corresponding optimization problems are all NPhard. For some of these versions we propose two optimization algorithms: (i) a practical heuristic technique which we call DijkstraGC, and (ii) a slow method based on problem decomposition which provides a lower bound on the problem. We use the second technique to verify that for some practical examples DijkstraGC is able to find the global minimum. 1.
Beyond pairwise energies: Efficient optimization for higherorder MRFs
 in IEEE Conference on Computer Vision and Pattern Recognition : CVPR
, 2009
"... In this paper, we introduce a higherorder MRF optimization framework. On the one hand, it is very general; we thus use it to derive a generic optimizer that can be applied to almost any higherorder MRF and that provably optimizes a dual relaxation related to the input MRF problem. On the other han ..."
Abstract

Cited by 81 (11 self)
 Add to MetaCart
(Show Context)
In this paper, we introduce a higherorder MRF optimization framework. On the one hand, it is very general; we thus use it to derive a generic optimizer that can be applied to almost any higherorder MRF and that provably optimizes a dual relaxation related to the input MRF problem. On the other hand, it is also extremely flexible and thus can be easily adapted to yield far more powerful algorithms when dealing with subclasses of highorder MRFs. We thus introduce a new powerful class of highorder potentials, which are shown to offer enough expressive power and to be useful for many vision tasks. To address them, we derive, based on the same framework, a novel and extremely efficient messagepassing algorithm, which goes beyond the aforementioned generic optimizer and is able to deliver almost optimal solutions of very high quality. Experimental results on vision problems demonstrate the extreme effectiveness of our approach. For instance, we show that in some cases we are even able to compute the global optimum for NPhard higherorder MRFs in a very efficient manner. 1.
On Dual Decomposition and Linear Programming Relaxations for Natural Language Processing
 In Proc. EMNLP
, 2010
"... This paper introduces dual decomposition as a framework for deriving inference algorithms for NLP problems. The approach relies on standard dynamicprogramming algorithms as oracle solvers for subproblems, together with a simple method for forcing agreement between the different oracles. The approa ..."
Abstract

Cited by 73 (3 self)
 Add to MetaCart
(Show Context)
This paper introduces dual decomposition as a framework for deriving inference algorithms for NLP problems. The approach relies on standard dynamicprogramming algorithms as oracle solvers for subproblems, together with a simple method for forcing agreement between the different oracles. The approach provably solves a linear programming (LP) relaxation of the global inference problem. It leads to algorithms that are simple, in that they use existing decoding algorithms; efficient, in that they avoid exact algorithms for the full model; and often exact, in that empirically they often recover the correct solution in spite of using an LP relaxation. We give experimental results on two problems: 1) the combination of two lexicalized parsing models; and 2) the combination of a lexicalized parsing model and a trigram partofspeech tagger. 1
Messagepassing for graphstructured linear programs: Proximal methods and rounding schemes
, 2008
"... The problem of computing a maximum a posteriori (MAP) configuration is a central computational challenge associated with Markov random fields. A line of work has focused on “treebased ” linear programming (LP) relaxations for the MAP problem. This paper develops a family of superlinearly convergen ..."
Abstract

Cited by 60 (0 self)
 Add to MetaCart
(Show Context)
The problem of computing a maximum a posteriori (MAP) configuration is a central computational challenge associated with Markov random fields. A line of work has focused on “treebased ” linear programming (LP) relaxations for the MAP problem. This paper develops a family of superlinearly convergent algorithms for solving these LPs, based on proximal minimization schemes using Bregman divergences. As with standard messagepassing on graphs, the algorithms are distributed and exploit the underlying graphical structure, and so scale well to large problems. Our algorithms have a doubleloop character, with the outer loop corresponding to the proximal sequence, and an inner loop of cyclic Bregman divergences used to compute each proximal update. Different choices of the Bregman divergence lead to conceptually related but distinct LPsolving algorithms. We establish convergence guarantees for our algorithms, and illustrate their performance via some simulations. We also develop two classes of graphstructured rounding schemes, randomized and deterministic, for obtaining integral configurations from the LP solutions. Our deterministic rounding schemes use a “reparameterization ” property of our algorithms so that when the LP solution is integral, the MAP solution can be obtained even before the LPsolver converges to the optimum. We also propose a graphstructured randomized rounding scheme that applies to iterative LP solving algorithms in general. We analyze the performance of our rounding schemes, giving bounds on the number of iterations required, when the LP is integral, for the rounding schemes to obtain the MAP solution. These bounds are expressed in terms of the strength of the potential functions, and the energy gap, which measures how well the integral MAP solution is separated from other integral configurations. We also report simulations comparing these rounding schemes. 1
Dense Nonrigid Surface Registration Using HighOrder Graph Matching
"... In this paper, we propose a highorder graph matching formulation to address nonrigid surface matching. The singleton terms capture the geometric and appearance similarities (e.g., curvature and texture) while the highorder terms model the intrinsic embedding energy. The novelty of this paper incl ..."
Abstract

Cited by 48 (11 self)
 Add to MetaCart
(Show Context)
In this paper, we propose a highorder graph matching formulation to address nonrigid surface matching. The singleton terms capture the geometric and appearance similarities (e.g., curvature and texture) while the highorder terms model the intrinsic embedding energy. The novelty of this paper includes: 1) casting 3D surface registration into a graph matching problem that combines both geometric and appearance similarities and intrinsic embedding information, 2) the first implementation of highorder graph matching algorithm that solves a nonconvex optimization problem, and 3) an efficient twostage optimization approach to constrain the search space for dense surface registration. Our method is validated through a series of experiments demonstrating its accuracy and efficiency, notably in challenging cases of large and/or nonisometric deformations, or meshes that are partially occluded. 1.
Parsing human motion with stretchable models. CVPR
, 2011
"... We address the problem of articulated human pose estimation in videos using an ensemble of tractable models with rich appearance, shape, contour and motion cues. In previous articulated pose estimation work on unconstrained videos, using temporal coupling of limb positions has made little to no dif ..."
Abstract

Cited by 44 (4 self)
 Add to MetaCart
(Show Context)
We address the problem of articulated human pose estimation in videos using an ensemble of tractable models with rich appearance, shape, contour and motion cues. In previous articulated pose estimation work on unconstrained videos, using temporal coupling of limb positions has made little to no difference in performance over parsing frames individually [8, 28]. One crucial reason for this is that joint parsing of multiple articulated parts over time involves intractable inference and learning problems, and previous work has resorted to approximate inference and simplified models. We overcome these computational and modeling limitations using an ensemble of tractable submodels which couple locations of body joints within and across frames using expressive cues. Each submodel is responsible for tracking a single joint through time (e.g., left elbow) and also models the spatial arrangement of all joints in a single frame. Because of the tree structure of each submodel, we can perform efficient exact inference and use rich temporal features that depend on image appearance, e.g., color tracking and optical flow contours. We propose and experimentally investigate a hierarchy of submodel combination methods, and we find that a highly efficient maxmarginal combination method outperforms much slower (by orders of magnitude) approximate inference using dual decomposition. We apply our pose model on a new video dataset of highly varied and articulated poses from TV shows. We show significant quantitative and qualitative improvements over stateoftheart singleframe pose estimation approaches. 1.
Joint optimization of segmentation and appearance models
, 2009
"... Many interactive image segmentation approaches use an objective function which includes appearance models as an unknown variable. Since the resulting optimization problem is NPhard the segmentation and appearance are typically optimized separately, in an EMstyle fashion. One contribution of this p ..."
Abstract

Cited by 40 (6 self)
 Add to MetaCart
(Show Context)
Many interactive image segmentation approaches use an objective function which includes appearance models as an unknown variable. Since the resulting optimization problem is NPhard the segmentation and appearance are typically optimized separately, in an EMstyle fashion. One contribution of this paper is to express the objective function purely in terms of the unknown segmentation, using higherorder cliques. This formulation reveals an interesting bias of the model towards balanced segmentations. Furthermore, it enables us to develop a new dual decomposition optimization procedure, which provides additionally a lower bound. Hence, we are able to improve on existing optimizers, and verify that for a considerable number of real world examples we even achieve global optimality. This is important since we are able, for the first time, to analyze the deficiencies of the model. Another contribution is to establish a property of a particular dual decomposition approach which involves convex functions depending on foreground area. As a consequence, we show that the optimal decomposition for our problem can be computed efficiently via a parametric maxflow algorithm. 1.