In this paper we address the problem of minimizing a large class of energy functions that occur in early vision. The major restriction is that the energy function’s smoothness term must only involve pairs of pixels. We propose two algorithms that use graph cuts to compute a local minimum even when very large moves are allowed. The first move we consider is an α-βswap: for a pair of labels α, β, this move exchanges the labels between an arbitrary set of pixels labeled α and another arbitrary set labeled β. Our first algorithm generates a labeling such that there is no swap move that decreases the energy. The second move we consider is an α-expansion: for a label α, this move assigns an arbitrary set of pixels the label α. Our second

Abstract. Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, two-frame stereo methods. Our taxonomy is designed to assess the different components and design decisions made in individual stereo algorithms. Using this taxonomy, we compare existing stereo methods and present experiments evaluating the performance of many different variants. In order to establish a common software platform and a collection of data sets for easy evaluation, we have designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms. We have also produced several new multi-frame stereo data sets with ground truth and are making both the code and data sets available on the Web. Finally, we include a comparative evaluation of a large set of today’s best-performing stereo algorithms.

Several new algorithms for visual correspondence based on graph cuts [7, 14, 17] 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 a new method which properly addresses occlusions, while preserving the advantages of graph cut algorithms. We give experimental results for stereo as well as motion, which demonstrate that our method performs well both at detecting occlusions and computing disparities.

While stereo matching was originally formulated as the recovery of 3D shape from a pair of images, it is now generally recognized that using more than two images can dramatically improve the quality of the reconstruction. Unfortunately, as more images are added, the prevalence of semioccluded regions (pixels visible in some but not all images) also increases. In this paper, we propose some novel techniques to deal with this problem. Our first idea is to use a combination of shiftable windows and a dynamically selected subset of the neighboring images to do the matches. Our second idea is to explicitly label occluded pixels within a global energy minimization framework, and to reason about visibility within this framework so that only truly visible pixels are matched. Experimental results show a dramatic improvement using the first idea over conventional multibaseline stereo, especially when used in conjunction with a global energy minimization technique. These results also show that explicit occlusion labeling and visibility reasoning do help, but not significantly, if the spatial and temporal selection is applied first.

We present the first constant-factor approximation algorithm for network design with multiple commodities and economies of scale. We consider the rent-or-buy problem, a type of multicommodity buy-at-bulk network design in which there are two ways to install capacity on any given edge. Capacity can be rented, with cost incurred on a perunit of capacity basis, or bought, which allows unlimited use after payment of a large fixed cost. Given a graph and a set of source-sink pairs, we seek a minimum-cost way of installing sufficient capacity on edges so that a prescribed amount of flow can be sent simultaneously from each source to the corresponding sink. Recent work on buy-at-bulk network design has concentrated on the special case where all sinks are identical; existing constant-factor approximation algorithms for this special case make crucial use of the assumption that all commodities ship flow to the same sink vertex and do not obviously extend to the multicommodity rent-or-buy problem. Prior to our work, the best heuristics for the multicommodity rent-or-buy problem achieved only logarithmic performance guarantees and relied on the machinery of relaxed metrical task systems or of metric embeddings. By contrast, we solve the network design problem directly via a novel primal-dual algorithm. 1

Optimization techniques based on graph cuts have become a standard tool for many vision applications. These techniques allow to minimize efficiently certain energy functions corresponding to pairwise Markov Random Fields (MRFs). Currently, there is an accepted view within the computer vision community that graph cuts can only be used for optimizing a limited class of MRF energies (e.g. submodular functions). In this survey we review some results that show that graph cuts can be applied to a much larger class of energy functions (in particular, non-submodular functions). While these results are well-known in the optimization community, to our knowledge they were not used in the context of computer vision and MRF optimization. We demonstrate the relevance of these results to vision on the problem of binary texture restoration.

Surface reconstruction from multiple calibrated images mainly has been approached using local methods, either as a continuous optimization problem driven by level sets, or by discrete volumetric methods such as space carving. We propose a direct surface reconstruction approach which starts from a continuous geometric functional that is minimized up to a discretization by a global graph-cut algorithm operating on a 3D embedded graph. The method is related to the stereo disparity computation based on graph-cut formulation, but fundamentally different in two aspects. First, existing stereo disparity methods are only interested in obtaining layers of constant disparity, while we focus on high resolution surface geometry. Second, most of the existing graph-cut algorithms only reach approximate solutions, while we guarantee a global minimum. The whole procedure is consistently incorporated into a voxel representation that handles both occlusions and discontinuities. We demonstrate our algorithm on real sequences, yielding remarkably detailed surface geometry up to 1/10th of a pixel.

Abstract. While many algorithms for computing stereo correspondence have been proposed, there has been very little work on experimentally evaluating algorithm performance, especially using real (rather than synthetic) imagery. In this paper we propose an experimental comparison of several different stereo algorithms. We use real imagery, and explore two different methodologies, with different strengths and weaknesses. Our first methodology is based upon manual computation of dense ground truth. Here we make use of a two stereo pairs: one of these, from the University of Tsukuba, contains mostly fronto-parallel surfaces; while the other, which we built, is a simple scene with a slanted surface. Our second methodology uses the notion of prediction error, which is the ability of a disparity map to predict an (unseen) third image, taken from a known camera position with respect to the input pair. We present results for both correlation-style stereo algorithms and techniques based on global methods such as energy minimization. Our experiments suggest that the two methodologies give qualitatively consistent results. Source images and additional materials, such as the implementations of various algorithms, are available on the web from

In this paper we introduce a novel and efficient approach to dense image registration, which does not require a derivative of the employed cost function. In such a context the registration problem is formulated using a discrete Markov Random Field objective function. First, towards dimensionality reduction on the variables we assume that the dense deformation field can be expressed using a small number of control points (registration grid) and an interpolation strategy. Then, the registration cost is expressed using a discrete sum over image costs (using an arbitrary similarity measure) projected on the control points, and a smoothness term that penalizes local deviations on the deformation field according to a neighborhood system on the grid. Towards a discrete approach the search space is quantized resulting in a fully discrete model. In order to account for large deformations and produce results on a high resolution level a multi-scale incremental approach is considered where the optimal solution is iteratively updated. This is done through successive morphings of the source towards the target image. Efficient linear programming using the primal dual principles is considered to recover the lowest potential of the cost function. Very promising results using synthetic data with known deformations and real data demonstrate the potentials of our approach.

A new framework is presented that uses tools from duality theory of linear programming to derive graph-cut based combinatorial algorithms for approximating NP-hard classification problems. The derived algorithms include α-expansion graph cut techniques merely as a special case, have guaranteed optimality properties even in cases where α-expansion techniques fail to do so and can provide very tight per-instance suboptimality bounds in all occasions. 1