Learn More
We consider the problem of optimizing multilabel MRFs, which is in general NP-hard and ubiquitous in low-level computer vision. One approach for its solution is to formulate it as an integer linear programming and relax the integrality constraints. The approach we consider in this paper is to first convert the multi-label MRF into an equivalent binary-label(More)
We propose a novel MRF-based model for deformable image matching. Given two images, the task is to estimate a mapping from one image to the other maximizing the quality of the match. We consider mappings defined by a discrete deformation field constrained to preserve 2D continuity. We pose the task as finding MAP configurations of a pairwise MRF. We propose(More)
We consider discrete pairwise energy minimization problem (weighted constraint satisfaction, max-sum labeling) and methods that identify a globally optimal partial assignment of variables. When finding a complete optimal assignment is intractable, determining optimal values for a part of variables is an interesting possibility. Existing methods are based on(More)
We consider the NP-hard problem of MAP-inference for graphical models. We propose a polynomial time practically efficient algorithm for finding a part of its optimal solution. Specifically, our algorithm marks each label in each node of the considered graphical model either as (i) optimal, meaning that it belongs to all optimal solutions of the inference(More)
We propose a novel distributed algorithm for the minimum cut problem. Motivated by applications like volumetric segmentation in computer vision, we aim at solving large sparse problems. When the problem does not fully fit in the memory, we need to either process it by parts, looking at one part at a time, or distribute across several computers. Many(More)
Most image labeling problems such as segmenta-tion and image reconstruction are fundamentally ill-posed and suffer from ambiguities and noise. Higher order image priors encode high level structural dependencies between pixels and are key to overcoming these problems. However, these priors in general lead to computationally intractable models. This paper(More)
We propose a novel MRF-based model for image matching. Given two images, the task is to estimate a mapping from one image to another, in order to maximize the matching quality. We consider mappings defined by discrete deformation field constrained to preserve 2-dimensional continuity. We approach the corresponding optimization problem by the TRW-S(More)
This paper presents a scalable multi-view stereo reconstruction method which can deal with a large number of large unorganized images in affordable time and effort. The computational effort of our technique is a linear function of the surface area of the observed scene which is conveniently discretized to represent sufficient but not excessive detail. Our(More)
We address the problem of energy minimization, which is (1) generally NP-complete and (2) involves many discrete variables – commonly a 2D array of them, arising from an MRF model. One of the approaches to the problem is to formulate it as integer linear programming and relax integrality constraints. However this can be done in a number of possible ways.(More)
We consider the problem of image matching under the unknown statistical dependence of the signals, i.e. a signal in one image may correspond to one or more signals in the other image with different probabilities. This problem is widely known as multimodal image registration and is commonly solved by the maximization of the empirical mutual information(More)