R. Zabih - Academia.edu (original) (raw)

Papers by R. Zabih

Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997

US Patent Jim. 12,2001 Sheet 1 of 4 US 6,246,790 Bl dmax FIG. ... US Patent Jim. 12,2001 Sheet 2 ... more US Patent Jim. 12,2001 Sheet 1 of 4 US 6,246,790 Bl dmax FIG. ... US Patent Jim. 12,2001 Sheet 2 of 4 US 6,246,790 Bl n I P1=(xry1) n FIG, 2 ... US Patent Jun. 12, 2001 Sheet 3 of 4 US 6,246,790 Bl o o -° o 2 •S£ 3^ O 70 Image 1, color 1 Image 1, color2 Image2, colorl FIG. 3

European Conference on Computer Vision, 2006

Lecture Notes in Computer Science, 2003

Reconstructing a 3-D scene from more than one camera is a classical problem in computer vision. O... more Reconstructing a 3-D scene from more than one camera is a classical problem in computer vision. One of the major sources of difficulty is the fact that not all scene elements are visible from all cameras. In the last few years, two promising approaches have been developed that formulate the scene reconstruction problem in terms of energy minimization, and minimize the energy using graph cuts. These energy minimization approaches treat the input images symmetrically, handle visibility constraints correctly, and allow spatial smoothness to be enforced. However, these algorithm propose different problem formulations, and handle a limited class of smoothness terms. One algorithm [11] uses a problem formulation that is restricted to two-camera stereo, and imposes smoothness between a pair of cameras. The other algorithm can handle an arbitrary number of cameras, but imposes smoothness only with respect to a single camera. In this paper we give a more general energy minimization formulation for the problem, which allows a larger class of spatial smoothness constraints. We show that our formulation includes both of the previous approaches as special cases, as well as permitting new energy functions. Experimental results on real data with ground truth are also included.

Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662), 2000

Voxel occupancy is one approach for reconstructing the 3-dimensional shape of an object from mult... more Voxel occupancy is one approach for reconstructing the 3-dimensional shape of an object from multiple views. In voxel occupancy, the task is to produce a binary labeling of a set of voxels, that determines which voxels are filled and which are empty. In this paper, we give an energy minimization formulation of the voxel occupancy problem. The global minimum of this energy can be rapidly computed with a single graph cut, using a result due to Greig, Porteous and Seheult [7]. The energy function we minimize contains a data term and a smoothness term. The data term is a sum over the individual voxels, where the penalty for a voxel is based on the observed intensities of the pixels that intersect it. The smoothness term is the number of empty voxels adjacent to filled ones. Our formulation can be viewed as a generalization of silhouette intersection, with two advantages: we do not compute silhouettes, which are a major source of errors; and we can naturally incorporate spatial smoothness. We give experimental results showing reconstructions from both real and synthetic imagery. Reconstruction using this smoothed energy function is not much more time consuming than simple silhouette intersection; it takes about 10 seconds to reconstruct a one million voxel volume.

Lecture Notes in Computer Science, 2002

In this paper we propose an extension to the standard Markov Random Field (MRF) model in order to... more In this paper we propose an extension to the standard Markov Random Field (MRF) model in order to handle layers. Our extension, which we call a Factorial MRF (FMRF), is analogous to the extension from Hidden Markov Models (HMM's) to Factorial HMM's. We present an efficient EM-based algorithm for inference on Factorial MRF's. Our algorithm makes use of the fact that layers are a priori independent, and that layers only interact through the observable image. The algorithm iterates between wide inference, i.e., inference within each layer for the entire set of pixels, and deep inference, i.e., inference through the layers for each single pixel. The efficiency of our method is partly due to the use of graph cuts for binary segmentation, which is part of the wide inference step. We show experimental results for both real and synthetic images.

The IEEE Computer Society is an association of people with professional interest in the field of ... more The IEEE Computer Society is an association of people with professional interest in the field of computers. All members of the IEEE are eligible for membership in the Computer Society, as are members of certain professional societies and other computer professionals. Computer Society members will receive this Transactions in print and online upon payment of the annual Society membership fee ($50 for IEEE members, 99forallothers)plusanannualsubscriptionfeeof99 for all others) plus an annual subscription fee of 99forallothers)plusanannualsubscriptionfeeof57. For additional membership and subscription information, visit our Web site at ...

An efficient navigator method is presented that substantially increases the scan efficiency while... more An efficient navigator method is presented that substantially increases the scan efficiency while maintaining the motion suppression effectiveness in magnetic resonance imaging. The method is achieved by simultaneously acquiring different image volumes at different motion states of the subject being scanned. A scheduling algorithm is used to assign volumes to position bins of a motion histogram of the subject. The motion histogram is periodically updated and the volumes are reassigned to position bins.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2006

High resolution 3D coronary artery MR angiography is time-consuming and can benefit from accelera... more High resolution 3D coronary artery MR angiography is time-consuming and can benefit from accelerated data acquisition provided by parallel imaging techniques without sacrificing spatial resolution. Currently, popular maximum likelihood based parallel imaging reconstruction techniques such as the SENSE algorithm offer this advantage at the cost of reduced signal-to-noise ratio (SNR). Maximum a posteriori (MAP) reconstruction techniques that incorporate globally smooth priors have been developed to recover this SNR loss, but they tend to blur sharp edges in the target image. The objective of this study is to demonstrate the feasibility of employing edge-preserving Markov random field priors in a MAP reconstruction framework, which can be solved efficiently using a graph cuts based optimization algorithm. The preliminary human study shows that our reconstruction provides significantly better SNR than the SENSE reconstruction performed by a commercially available scanner for navigator g...

Radiology, 2002

The purpose of this study was to improve dynamic two-dimensional projection magnetic resonance di... more The purpose of this study was to improve dynamic two-dimensional projection magnetic resonance digital subtraction angiography by using remasking and filtering postprocessing techniques. Four methods were evaluated in 50 patients: default mask subtraction, remasked subtraction, filtering based on the SD, and linear filtering. The results demonstrated that postprocessing techniques such as linear filtering can reduce background motion artifacts and improve arterial contrast-to-noise ratio.

Magnetic Resonance in Medicine, 2002

For time-resolved background-subtracted contrast-enhanced magnetic resonance angiography, the bri... more For time-resolved background-subtracted contrast-enhanced magnetic resonance angiography, the bright and sparse arterial signal allows unique identification of contrast bolus arrival in the arteries. This article presents an automatic filtering algorithm using such arterial characterization for selecting arterial phase images and mask images to generate an optimal summary arteriogram. A paired double-blinded comparison demonstrated that this automatic algorithm is as effective as the manual process.

Magnetic Resonance in Medicine, 2004

The simultaneous multiple volume (SMV) approach in navigator-gated MRI allows the use of the whol... more The simultaneous multiple volume (SMV) approach in navigator-gated MRI allows the use of the whole motion range or the entire scan time for the reconstruction of final images by simultaneously acquiring different image volumes at different motion states. The motion tolerance range for each volume is kept small, thus SMV substantially increases the scan efficiency of navigator methods while maintaining the effectiveness of motion suppression. This article reports a general implementation of the SMV approach using a multiprocessor scheduling algorithm. Each motion state is regarded as a processor and each volume is regarded as a job. An efficient scheduling that completes all jobs in minimal time is maintained even when the motion pattern changes. Initial experiments demonstrated that SMV significantly increased the scan efficiency of navigatorgated MRI. Magn Reson Med 52:362-367, 2004.

Magnetic Resonance Imaging, 2003

Navigator gating techniques can effectively reduce motion effects in MRI by accepting data only w... more Navigator gating techniques can effectively reduce motion effects in MRI by accepting data only when the object is in a small range of positions at the cost of significantly prolonging scan time. A simultaneous multiple volume (SMV) algorithm is reported here that can substantially increase the scan efficiency while maintaining the effectiveness of motion suppression. This is achieved by acquiring different image volumes at different motion states. Initial experiments demonstrate that SMV can significantly increase the scan efficiency of navigator MRI.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000

One of the most exciting advances in early vision has been the development of efficient energy mi... more One of the most exciting advances in early vision has been the development of efficient energy minimization algorithms. Many early vision tasks require labeling each pixel with some quantity such as depth or texture. While many such problems can be elegantly expressed in the language of Markov Random Fields (MRF's), the resulting energy minimization problems were widely viewed as intractable. Recently, algorithms such as graph cuts and loopy belief propagation (LBP) have proven to be very powerful: for example, such methods form the basis for almost all the top-performing stereo methods. Unfortunately, most papers define their own energy function, which is minimized with a specific algorithm of their choice. As a result, the tradeoffs among different energy minimization algorithms are not well understood. In this paper we describe a set of energy minimization benchmarks, which we use to compare the solution quality and running time of several common energy minimization algorithms. We investigate three promising recent methods-graph cuts, LBP, and tree-reweighted message passing-as well as the well-known older iterated conditional modes (ICM) algorithm. Our benchmark problems are drawn from published energy functions used for stereo, image stitching and interactive segmentation. We also provide a general-purpose software interface that allows vision researchers to easily switch between optimization methods with minimal overhead. We expect that the availability of our benchmarks and interface will make it significantly easier for vision researchers to adopt the best method for their specific problems. Benchmarks, code, results and images are available at http://vision.middlebury.edu/MRF.

IEEE Transactions on Dependable and Secure Computing, 2000

ABSTRACT

ACM Transactions on Programming Languages and Systems, 1992

In time-resolved contrast-enhanced magnetic resonance angiography, a measure quantifying image qu... more In time-resolved contrast-enhanced magnetic resonance angiography, a measure quantifying image quality provides a basis for generating a linear filtered composite image by facilitating selection of a mask and an arterial phase image for subtraction. Filtering of individual pixels of a temporal series of images provides enhanced contrast in a single image by allowing the temporal behavior of the pixel intensity to denote representation as an artery, vein or background tissue. Motion artifacts are suppressed by re-registering ...