[2] C. Rother, V. Kolmogorov, A. Blake: ”Grabcut: Interactive Foreground Extraction Using Iterated Graph Cuts”, SIGGRAPH 2004 [3] Y. Boykov, M. P. Jolly: ”Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in n-d Images”, ICCV 2001 Minimize Energy E on 3D grid [3]: E(x) = ∑ i∈V φi(xi) } {{ } Regional Costs + ∑ (i,j)∈E φi,j(xi, xj) } {{ } Boundary Costs Feature Tracking...

This work is partially funded by the German Research Foundation (RO 2497/6-1). [1] Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision, TPAMI 2004 [2] Boykov, Y., Jolly, M.: Interactive graph cuts for optimal boundary & region segmentation of objects in nd images, ICCV 2001 [3] Rother, C., Kolmogorov, V., Blake, A.: Grabcut: In...

Several algorithms are common for estimating depth from stereo series, but many of them have difficulties when determining depth of objects having periodical structure. This contribution proposes a method to overcome the impediments by using defocus as additional information. The algorithm fuses depth from stereo and depth from defocused edges by analyzing and evaluating image series with simul...

Several new algorithms for visual correspondence based on graph cuts [6, 13, 16] have recently been developed. While these methods give very strong results in practice, they do not handle occlusions properly. Specifically, they treat the two input images asymmetrically, and they do not ensure that a pixel corresponds to at most one pixel in the other image. In this paper, we present two new met...

In this paper, we consider the problem of evaluating (s, t)-cuts in a bounded treewidth graph. In particular, we show how to compute the partition function for weighted cuts of the graph, i.e., the total weight of all (s, t)-cuts where the weight of a single cut is the product of its edge weights. This method can also easily be adapted to work with additive weights for the cost of a cut. We als...

This paper establishes the consistency of a family of graph-cut-based algorithms for clustering of data clouds. We consider point clouds obtained as samples of a ground-truth measure. We investigate approaches to clustering based on minimizing objective functionals defined on proximity graphs of the given sample. Our focus is on functionals based on graph cuts like the Cheeger and ratio cuts. W...

We prove that every cubic bridgeless graph G contains a 2-factor which intersects all (minimal) edge-cuts of size 3 or 4. This generalizes an earlier result of the authors, namely that such a 2-factor exists provided that G is planar. As a further extension, we show that every graph contains a cycle (a union of edge-disjoint circuits) that intersects all edge-cuts of size 3 or 4. Motivated by t...

Recently, graph cuts algorithms have been used to solve variational image restoration problems, especially for noise removal and segmentation. Compared to time-marching PDE methods, graph cuts based methods are more efficient and able to obtain the global minimizer. However, for high resolution and large-scale images, the cost of both memory and computational time increases dramatically. In thi...

We study the space complexity of sketching cuts and Laplacian quadratic forms of graphs. We show that any data structure which approximately stores the sizes of all cuts in an undirected graph on n vertices up to a 1 + ǫ error must use Ω(n logn/ǫ) bits of space in the worst case, improving the Ω(n/ǫ) bound of [ACK16] and matching the best known upper bound achieved by spectral sparsifiers [BSS1...

Stereo vision is one of the central research problems in computer vision. The most difficult and important issue in this area is the stereo matching process. One technique that performs this process is the Graph-Cuts based algorithm and which provides accurate results [1]. Nevertheless, this approach is too slow to use due to the redundant computations that it invokes. In this work, an Adaptive...