Olga Veksler

Details der Publikationsliste

Zeitraum

1997 - 2009

Anzahl

47

Co-Autoren

A Comparative Study of Energy Minimization Methods for Markov Random Fields with (2009)

Smoothness-based Priors, Richard Szeliski, Ramin Zabih, Senior Member, Daniel Scharstein, Olga Veksler, ...

Abstract—Among the most exciting advances in early vision has been the development of efficient energy minimization algorithms for pixel-labeling tasks such as depth or texture computation. It has...

A Comparative Study of Energy Minimization Methods for Markov Random Fields with (2009)

Smoothness-based Priors, Richard Szeliski, Ramin Zabih, Senior Member, Daniel Scharstein, Olga Veksler, ...

Abstract—Among the most exciting advances in early vision has been the development of efficient energy minimization algorithms for pixel-labeling tasks such as depth or texture computation. It has...

100 “Math. Models of C.Vision: The Handbook”, edts. Paragios, Chen, Faugeras Graph Cuts in Vision and Graphics: Theories and Applications (2008)

Yuri Boykov, Olga Veksler

Abstract. Combinatorial min-cut algorithms on graphs emerged as an increasingly useful tool for problems in vision. Typically, the use of graphcuts is motivated by one of the following two reasons....

100 “Math. Models of C.Vision: The Handbook”, edts. Paragios, Chen, Faugeras Graph Cuts in Vision and Graphics: Theories and Applications (2008)

Yuri Boykov, Olga Veksler

Abstract. Combinatorial min-cut algorithms on graphs emerged as an increasingly useful tool for problems in vision. Typically, the use of graphcuts is motivated by one of the following two reasons....

Simulating Classic Mosaics with Graph Cuts (2008)

Yu Liu, Olga Veksler, Olivier Juan

Abstract. Classic mosaic is one of the oldest and most durable art forms. There has been a growing interest in simulating classic mosaics from digital images recently. To be visually pleasing, a...

Visual Correspondence by Compact Windows via Minimum Ratio Cycle (2007)

Olga Veksler

One of the earliest and still widely used methods for establishing dense visual correspondence is based on matching windows of pixels. The major diculty of this method is choosing a window of...

Professional Experience (2007)

Olga Veksler

honors) and Computer Science. (with honors)

A comparative study of energy minimization methods for Markov random fields (2006)

Richard Szeliski, Ramin Zabih, Daniel Scharstein, Olga Veksler, Aseem Agarwala, Carsten Rother

Abstract. 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...

A comparative study of energy minimization methods for Markov random fields (2006)

Richard Szeliski, Olga Veksler, Vladimir Kolmogorov, Aseem Agarwala, Carsten Rother

Abstract. 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...

A comparative study of energy minimization methods for Markov random fields (2006)

Rick Szeliski, Olga Veksler, Aseem Agarwala, Carsten Rother

Abstract. 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...

Stereo correspondence by dynamic programming on a tree (2005)

Olga Veksler

Dynamic programming on a scanline is one of the oldest and still popular methods for stereo correspondence. While efficient, its performance is far from the state of the art because the vertical...

Fast Variable Window for Stereo Correspondence using Integral Images (2003)

Olga Veksler

We develop a fast and accurate variable window approach. The two main ideas for achieving accuracy are choosing a useful range of window sizes/shapes for evaluation and developing a new window cost...

Fast variable window for stereo correspondence using integral images (2003)

Olga Veksler

We develop a fast and accurate variable window approach. The two main ideas for achieving accuracy are choosing a useful range of window sizes/shapes for evaluation and developing a new window cost...

Dense features for semi-dense stereo correspondence (2002)

Olga Veksler

We present a new feature based algorithm for stereo correspondence. Most of the previous feature based methods match sparse features like edge pixels, producing only sparse disparity maps. Our...

Fast approximate energy minimization via graph cuts (2001)

Yuri Boykov, Olga Veksler, Ramin Zabih

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...

Fast approximate energy minimization via graph cuts (2001)

Yuri Boykov, Olga Veksler, Ramin Zabih

Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. A common constraint is that the labels should vary smoothly almost everywhere while preserving sharp...

Fast approximate energy minimization via graph cuts (2001)

Yuri Boykov, Olga Veksler, Ramin Zabih

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...

Fast approximate energy minimization via graph cuts (2001)

Yuri Boykov, Olga Veksler, Ramin Zabih

AbstractÐMany tasks in computer vision involve assigning a label (such as disparity) to every pixel. A common constraint is that the labels should vary smoothly almost everywhere while preserving...

Fast approximate energy minimization via graph cuts (2001)

Yuri Boykov, Olga Veksler, Ramin Zabih

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...

Fast approximate energy minimization via graph cuts (2001)

Yuri Boykov, Olga Veksler, Ramin Zabih

Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. A common constraint is that the labels should vary smoothly almost everywhere while preserving sharp...

Semi-Dense Stereo Correspondence with Dense Features (2001)

Olga Veksler

We present a new feature based algorithm for stereo correspondence. Most of the previous feature based methods match sparse features like edge pixels, producing only sparse disparity maps. Our...

Stereo matching by compact windows via minimum ratio cycle (2001)

Olga Veksler

Window size and shape selection is a difficult problem in area based stereo. We propose an algorithm which chooses an appropriate window shape by optimizing over a large class of "compact...

Fast approximate energy minimization via graph cuts (2001)

Yuri Boykov, Olga Veksler, Ramin Zabih

AbstractÐMany tasks in computer vision involve assigning a label (such as disparity) to every pixel. A common constraint is that the labels should vary smoothly almost everywhere while preserving...

Image segmentation by nested cuts (2000)

Olga Veksler

We present a new image segmentation algorithm based on graph cuts. Our main tool is separation of each pixel p from a special point outside the image by a cut of a minimum cost. Such a cut creates a...

A new algorithm for energy minimization with discontinuities (1999)

Yuri Boykov, Olga Veksler, Ramin Zabih

Abstract. Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. These tasks can be formulated as energy minimization problems. In this paper, we consider a...

Fast Approximate Energy Minimization via Graph Cuts (1999)

Yuri Boykov, Olga Veksler, Ramin Zabih

Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. A common constraint is that the labels should vary smoothly almost everywhere. These tasks are naturally...

Fast Approximate Energy Minimization via Graph Cuts (1999)

Yuri Boykov, Olga Veksler, Ramin Zabih

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...

A New Algorithm for Energy Minimization with Discontinuities (1999)

Yuri Boykov Olga, Olga Veksler, Ramin Zabih

Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. These tasks can be formulated as energy minimization problems. In this paper, we consider a natural class...

A New Algorithm for Energy Minimization with Discontinuities (1999)

Yuri Boykov, Olga Veksler, Ramin Zabih

. Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. These tasks can be formulated as energy minimization problems. In this paper, we consider a natural class...

Markov random fields with efficient approximations (1998)

Yuri Boykov, Olga Veksler, Ramin Zabih

Markov Random Fields (MRF’s) can be used for a wide variety of vision problems. In this paper we focus on MRF’s with two-valued clique potentials, which form a generalized Potts model. We show...

A variable window approach to early vision (1998)

Yuri Boykov, Olga Veksler, Student Member, Ramin Zabih

Abstract—Early vision relies heavily on rectangular windows for tasks such as smoothing and computing correspondence. While rectangular windows are efficient, they yield poor results near object...

Efficient restoration of multicolor image with independent noise (1998)

Yuri Boykov, Olga Veksler, Ramin Zabih

We consider the problem of maximum a posteriori (MAP) restoration of multicolor images where each pixel has been degraded by independent arbitrary noise. We assume that the prior distribution is...

A variable window approach to early vision (1998)

Yuri Boykov, Olga Veksler, Ramin Zabih

correspondence Early vision relies heavily on rectangular windows for tasks such as smoothing and computing correspondence. While rectangular windows are efficient, they yield poor results near...

Markov random fields with efficient approximations (1998)

Yuri Boykov, Olga Veksler, Ramin Zabih

Markov Random Fields (MRF's) can be used for a wide variety of vision problems. In this paper we focus on MRF's with two-valued clique potentials, which form a generalized Potts model. We...

A Variable Window Approach to Early Vision (1998)

Yuri Boykov, Olga Veksler, Ramin Zabih

Early vision relies heavily on rectangular windows for tasks such as smoothing and computing correspondence. While rectangular windows are e#cient, they yield poor results near object boundaries. We...

Efficient Restoration of Multicolor Images with Independent Noise (1998)

Yuri Boykov, Olga Veksler, Ramin Zabih

We consider the problem of maximum a posteriori (MAP) restoration of multicolor images where each pixel has been degraded by independent arbitrary noise. We assume that the prior distribution is...

Markov random fields with efficient approximations (1998)

Yuri Boykov, Olga Veksler, Ramin Zabih

Markov Random Fields (MRF’s) can be used for a wide variety of vision problems. In this paper we focus on MRF’s with two-valued clique potentials, which form a generalized Potts model. We show...

Markov random fields with efficient approximations (1998)

Yuri Boykov, Olga Veksler, Ramin Zabih

Markov Random Fields (MRF’s) can be used for a wide variety of vision problems. In this paper we focus on MRF’s with two-valued clique potentials, which form a generalized Potts model. We show...

A Variable Window Approach to Early Vision (1997)

Boykov, Yuri, Veksler, Olga, Zabih, Ramin

Early vision relies heavily on rectangular windows for tasks such as smoothing and computing correspondence. While rectangular windows are efficient, they yield poor results near object boundaries....

Markov Random Fields with Efficient Approximations (1997)

Boykov, Yuri, Veksler, Olga, Zabih, Ramin

Markov Random Fields (MRF's) can be used for a wide variety of vision problems. In this paper we address the estimation of first-order MRF's with a particular clique potential that resembles a well....

A Variable Window Approach to Early Vision (1997)

Boykov, Yuri, Veksler, Olga, Zabih, Ramin

Early vision relies heavily on rectangular windows for tasks such as smoothing and computing correspondence. While rectangular windows are efficient, they yield poor results near object boundaries....

Markov Random Fields with Efficient Approximations (1997)

Boykov, Yuri, Veksler, Olga, Zabih, Ramin

Markov Random Fields (MRF's) can be used for a wide variety of vision problems. In this paper we address the estimation of first-order MRF's with a particular clique potential that resembles a well....

Disparity component matching for visual correspondence (1997)

Yuri Boykov, Olga Veksler, Ramin Zabih

We present a method for computing dense visual correspondence based on general assumptions about scene geometry. Our algorithm does not rely on correlation, and uses a variable region of support. We...

Disparity Component Matching for Visual Correspondence (1997)

Yuri Boykov, Olga Veksler, Ramin Zabih

We present a method for computing dense visual correspondence based on general assumptions about scene geometry. Our algorithm does not rely on correlation, and uses a variable region of support. We...

Disparity Component Matching for Visual Correspondence (1997)

Yuri Boykov, Olga Veksler, Ramin Zabih

We present a method for computing dense visual correspondence based on general assumptions about scene geometry. Our algorithm does not rely on correlation, and uses a variable region of support. We...

Disparity component matching for visual correspondence (1997)

Yuri Boykov, Olga Veksler, Ramin Zabih

We present a method for computing dense visual correspondence based on general assumptions about scene geometry. Our algorithm does not rely on correlation, and uses a variable region of support. We...

Energy Minimization with Discontinuities

Yuri Boykov, Olga Veksler, Ramin Zabih

Many tasks in computer vision can be formulated as energy minimization problems. In this paper, we consider a natural class of energy functions that permits discontinuities. We show that minimizing...