Learn More
We propose a novel method to obtain a part of an optimal non-relaxed integral solution for energy minimization problems with Potts interactions, known also as the minimal partition problem. The method empirically outperforms previous approaches like MQPBO and Kovtun's method in most of our test instances and especially in hard ones. As a starting point our(More)
—We consider the NP-hard problem of MAP-inference for graphical models. We propose a polynomial time and 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(More)
We present novel variational approaches for segmenting and cosegmenting images. Our supervised segmentation approach extends the classical Continuous Cut approach by a global appearance-based data term enforcing closeness of aggregated appearance statistics to a given prior model. This novel data term considers non-spatial, deformation-invariant statistics(More)
We consider energy minimization for undirected graphical models, known as MAP-or MLE-inference. We propose a novel method of combining combinatorial and convex programming techniques to obtain an optimal integer solution of the initial combinatorial problem. Our method enables to confine the application of the combinatorial solver to a small fraction of the(More)
We present a novel variational approach to image restoration (e.g., denoising, inpainting, labeling) that enables us to complement established variational approaches with a histogram-based prior, enforcing closeness of the solution to some given empirical measure. By minimizing a single objective function, the approach utilizes simultaneously two quite(More)
We exploit recent progress on globally optimal MAP inference by integer programming and perturbation-based approximations of the log-partition function. This enables to locally represent uncertainty of image partitions by approximate marginal distributions in a mathematically substantiated way, and to rectify local data term cues so as to close contours and(More)
We propose a general dual ascent framework for La-grangean decomposition of combinatorial problems. Although methods of this type have shown their efficiency for a number of problems, so far there was no general algorithm applicable to multiple problem types. In this work, we propose such a general algorithm. It depends on several parameters , which can be(More)