Search For:

Displaying 1-38 out of 38 total
Multi-operator media retargeting
Found in: ACM Transactions on Graphics (TOG)
By Ariel Shamir, Michael Rubinstein, Shai Avidan, Ariel Shamir, Michael Rubinstein, Shai Avidan, Ariel Shamir, Michael Rubinstein, Shai Avidan, Ariel Shamir, Michael Rubinstein, Shai Avidan
Issue Date:July 2009
pp. 1-2
Content aware resizing gained popularity lately and users can now choose from a battery of methods to retarget their media. However, no single retargeting operator performs well on all images and all target sizes. In a user study we conducted, we found tha...
     
Space-Time Tradeoffs in Photo Sequencing
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Tali Dekel,Yael Moses,Shai Avidan
Issue Date:December 2013
pp. 977-984
Photo-sequencing is the problem of recovering the temporal order of a set of still images of a dynamic event, taken asynchronously by a set of uncalibrated cameras. Solving this problem is a first, crucial step for analyzing (or visualizing) the dynamic co...
 
DCSH - Matching Patches in RGBD Images
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Yaron Eshet,Simon Korman,Eyal Ofek,Shai Avidan
Issue Date:December 2013
pp. 89-96
We extend patch based methods to work on patches in 3D space. We start with Coherency Sensitive Hashing (CSH), which is an algorithm for matching patches between two RGB images, and extend it to work with RGBD images. This is done by warping all 3D patches...
 
Coherency Sensitive Hashing
Found in: Computer Vision, IEEE International Conference on
By Simon Korman,Shai Avidan
Issue Date:November 2011
pp. 1607-1614
Coherency Sensitive Hashing (CSH) extends Locality Sensitivity Hashing (LSH) and PatchMatch to quickly find matching patches between two images. LSH relies on hashing, which maps similar patches to the same bin, in order to find matching patches. PatchMatc...
 
Geometrically consistent stereo seam carving
Found in: Computer Vision, IEEE International Conference on
By Tali Basha,Yael Moses,Shai Avidan
Issue Date:November 2011
pp. 1816-1823
Image retargeting algorithms attempt to adapt the image content to the screen without distorting the important objects in the scene. Existing methods address retargeting of a single image. In this paper we propose a novel method for retargeting a pair of s...
 
CG2Real: Improving the Realism of Computer Generated Images Using a Large Collection of Photographs
Found in: IEEE Transactions on Visualization and Computer Graphics
By Micah K. Johnson, Kevin Dale, Shai Avidan, Hanspeter Pfister, William T. Freeman, Wojciech Matusik
Issue Date:September 2011
pp. 1273-1285
Computer-generated (CG) images have achieved high levels of realism. This realism, however, comes at the cost of long and expensive manual modeling, and often humans can still distinguish between CG and real images. We introduce a new data-driven approach ...
 
An eye for an eye: A single camera gaze-replacement method
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lior Wolf, Ziv Freund, Shai Avidan
Issue Date:June 2010
pp. 817-824
The camera in video conference systems is typically positioned above, or below, the screen, causing the gaze of the users to appear misplaced. We propose an effective solution to this problem that is based on replacing the eyes of the user. This replacemen...
 
A probabilistic image jigsaw puzzle solver
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Taeg Sang Cho, Shai Avidan, William T. Freeman
Issue Date:June 2010
pp. 183-190
We explore the problem of reconstructing an image from a bag of square, non-overlapping image patches, the jigsaw puzzle problem. Completing jigsaw puzzles is challenging and requires expertise even for humans, and is known to be NP-complete. We depart fro...
 
The Patch Transform
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Taeg Sang Cho, Shai Avidan, William T. Freeman
Issue Date:August 2010
pp. 1489-1501
The patch transform represents an image as a bag of overlapping patches sampled on a regular grid. This representation allows users to manipulate images in the patch domain, which then seeds the inverse patch transform to synthesize modified images. Possib...
 
Creating and exploring a large photorealistic virtual space
Found in: Computer Vision and Pattern Recognition Workshop
By Josef Sivic, Biliana Kaneva, Antonio Torralba, Shai Avidan, William T. Freeman
Issue Date:June 2008
pp. 1-8
We present a system for exploring large collections of photos in a virtual 3D space. Our system does not assume the photographs are of a single real 3D location, nor that they were taken at the same time. Instead, we organize the photos in themes, such as ...
 
The patch transform and its applications to image editing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Taeg Sang Cho, Moshe Butman, Shai Avidan, William T. Freeman
Issue Date:June 2008
pp. 1-8
We introduce the patch transform, where an image is broken into non-overlapping patches, and modifications or constraints are applied in the “patch domain”. A modified image is then reconstructed from the patches, subject to those constraints. When no cons...
 
Synthetic Aperture Tracking: Tracking through Occlusions
Found in: Computer Vision, IEEE International Conference on
By Neel Joshi, Shai Avidan, Wojciech Matusik, David J. Kriegman
Issue Date:October 2007
pp. 1-8
Occlusion is a significant challenge for mnany tracking algorithms. Most current methods can track through transient occlusion, but cannot handle significant extendednded occlusion when the object's trajectory may change significantly. We present a method ...
 
Fast Pixel/Part Selection with Sparse Eigenvectors
Found in: Computer Vision, IEEE International Conference on
By Baback Moghaddam, Yair Weiss, Shai Avidan
Issue Date:October 2007
pp. 1-8
We extend the
 
Statistics of Infrared Images
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Nigel J. W. Morris, Shai Avidan, Wojciech Matusik, Hanspeter Pfister
Issue Date:June 2007
pp. 1-7
The proliferation of low-cost infrared cameras gives us a new angle for attacking many unsolved vision problems by leveraging a larger range of the electromagnetic spectrum. A first step to utilizing these images is to explore the statistics of infrared im...
 
Exploring Defocus Matting: Nonparametric Acceleration, Super-Resolution, and Off-Center Matting
Found in: IEEE Computer Graphics and Applications
By Neel Joshi, Wojciech Matusik, Shai Avidan, Hanspeter Pfister, William T. Freeman
Issue Date:March 2007
pp. 43-52
Defocus matting is a fully automatic and passive method for pulling mattes from video captured with coaxial cameras that have different depths of field and planes of focus. Nonparametric sampling can accelerate the video-matting process from minutes to sec...
 
Ensemble Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Shai Avidan
Issue Date:February 2007
pp. 261-271
We consider tracking as a binary classification problem, where an ensemble of weak classifiers is trained online to distinguish between the object and the background. The ensemble of weak classifiers is combined into a strong classifier using AdaBoost. The...
 
Fast Human Detection Using a Cascade of Histograms of Oriented Gradients
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Qiang Zhu, Mei-Chen Yeh, Kwang-Ting Cheng, Shai Avidan
Issue Date:June 2006
pp. 1491-1498
We integrate the cascade-of-rejectors approach with the Histograms of Oriented Gradients (HoG) features to achieve a fast and accurate human detection system. The features used in our system are HoGs of variable-size blocks that capture salient features of...
 
Learning a Sparse, Corner-Based Representation for Time-varying Background Modeling
Found in: Computer Vision, IEEE International Conference on
By Qiang Zhu, Shai Avidan, Kwang-Ting Cheng
Issue Date:October 2005
pp. 678-685
Time-varying phenomenon, such as ripples on water, trees waving in the wind and illumination changes, produces false motions, which significantly compromises the performance of an outdoor-surveillance system. In this paper, we propose a corner-based backgr...
 
Ensemble Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shai Avidan
Issue Date:June 2005
pp. 494-501
We consider tracking as a binary classification problem, where an ensemble of weak classifiers is trained on-line to distinguish between the object and the background. The ensemble of weak classifiers is combined into a strong classifier using AdaBoost. Th...
 
Support Vector Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Shai Avidan
Issue Date:August 2004
pp. 1064-1072
<p><b>Abstract</b>—Support Vector Tracking (<b>SVT</b>) integrates the Support Vector Machine (<b>SVM</b>) classifier into an optic-flow-based tracker. Instead of minimizing an intensity difference function between...
 
Joint Feature-Basis Subset Selection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shai Avidan
Issue Date:July 2004
pp. 283-290
We treat feature selection and basis selection in a unified framework by introducing the masking matrix. If one considers feature selection as finding a binary mask vector that determines which features participate in the learning process, and similarly, b...
 
Subset Selection for Efficient SVM Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shai Avidan
Issue Date:June 2003
pp. 85
We update the SVM score of an object through a video sequence with a small and variable subset of support vectors. In the first frame we use all the support vectors to compute the SVM score of the object but in subsequent frames we use only a small and var...
 
Manifold Pursuit: A New Approach to Appearance Based Recognition
Found in: Pattern Recognition, International Conference on
By Amnon Shashua, Anat Levin, Shai Avidan
Issue Date:August 2002
pp. 30590
<p>Manifold Pursuit (MP) extends Principal Component Analysis to be invariant to a desired group of image-plane transformations of an ensemble of un-aligned images.</p> <p>We derive a simple technique for projecting a misaligned target im...
 
Support Vector Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shai Avidan
Issue Date:December 2001
pp. 184
Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account ...
 
Layer Extraction from Multiple Images Containing Reflections and Transparency
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Richard Szeliski, Shai Avidan, P. Anandan
Issue Date:June 2000
pp. 1246
Many natural images contain reflections and transparency, i.e., they contain mixtures of reflected and transmitted light. When viewed from a moving camera, these appear as the superposition of component layer images moving relative to each other. The probl...
 
Trajectory Triangulation: 3D Reconstruction of Moving Points from a Monocular Image Sequence
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Shai Avidan, Amnon Shashua
Issue Date:April 2000
pp. 348-357
<p><b>Abstract</b>—We consider the problem of reconstructing the 3D coordinates of a moving point seen from a monocular moving camera, i.e., to reconstruct moving objects from line-of-sight measurements only. The task is feasible only whe...
 
Trajectory Triangulation over Conic Sections
Found in: Computer Vision, IEEE International Conference on
By Amnon Shashua, Shai Avidan, Michael Werman
Issue Date:September 1999
pp. 330
We consider the problem of reconstructing the 3D coordinates of a moving point seen from a monocular moving camera, i.e., to reconstruct moving objects from line-of-sight measurements only. The task is feasible only when some constraints are placed on the ...
 
Trajectory Triangulation of Lines: Reconstruction of a 3D point Moving along a Line from a Monocular Image Sequence
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shai Avidan, Amnon Shashua
Issue Date:June 1999
pp. 2062
We consider the problem of reconstructing the location of a moving 3D point seen from a monocular moving camera, i.e., to reconstruct moving objects from line-of-sight measurements only. Since the point is moving while the camera is moving, then even if th...
 
Novel View Synthesis by Cascading Trilinear Tensors
Found in: IEEE Transactions on Visualization and Computer Graphics
By Shai Avidan, Amnon Shashua
Issue Date:October 1998
pp. 293-306
<p><b>Abstract</b>—We present a new method for synthesizing novel views of a 3D scene from two or three reference images in full correspondence. The core of this work is the use and manipulation of an algebraic entity termed <it>the...
 
FasT-Match: Fast Affine Template Matching
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Simon Korman,Daniel Reichman,Gilad Tsur,Shai Avidan
Issue Date:June 2013
pp. 2331-2338
Fast-Match is a fast algorithm for approximate template matching under 2D affine transformations that minimizes the Sum-of-Absolute-Differences (SAD) error measure. There is a huge number of transformations to consider but we prove that they can be sampled...
 
Boundary snapping for robust image cutouts
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Eyal Zadicario, Shai Avidan, Alon Shmueli, Daniel Cohen-Or
Issue Date:June 2008
pp. 1-8
Boundary Snapping is an interactive image cutout algorithm that requires a small number of user supplied control points, or landmarks, to infer the cutout contour. The key idea is to match the appearance of all points along the desired contour to the landm...
 
Multi-operator media retargeting
Found in: ACM SIGGRAPH 2009 papers (SIGGRAPH '09)
By Ariel Shamir, Michael Rubinstein, Shai Avidan
Issue Date:August 2009
pp. 3-3
Content aware resizing gained popularity lately and users can now choose from a battery of methods to retarget their media. However, no single retargeting operator performs well on all images and all target sizes. In a user study we conducted, we found tha...
     
Seam carving for media retargeting
Found in: Communications of the ACM
By Ariel Shamir, Shai Avidan
Issue Date:January 2009
pp. 101-104
Traditional image resizing techniques are oblivious to the content of the image when changing its width or height. In contrast, media (i.e., image and video) retargeting take s content into account. For example, one would like to change the aspect ratio of...
     
Improved seam carving for video retargeting
Found in: ACM Transactions on Graphics (TOG)
By Ariel Shamir, Michael Rubinstein, Shai Avidan
Issue Date:August 2008
pp. 1-49
Video, like images, should support content aware resizing. We present video retargeting using an improved seam carving operator. Instead of removing 1D seams from 2D images we remove 2D seam manifolds from 3D space-time volumes. To achieve this we replace ...
     
Seam carving for content-aware image resizing
Found in: ACM Transactions on Graphics (TOG)
By Ariel Shamir, Shai Avidan
Issue Date:July 2007
pp. 1-35
Effective resizing of images should not only use geometric constraints, but consider the image content as well. We present a simple image operator called seam carving that supports content-aware image resizing for both reduction and expansion. A seam is an...
     
Natural video matting using camera arrays: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: ACM SIGGRAPH 2006 Papers (SIGGRAPH '06)
By Neel Joshi, Shai Avidan, Wojciech Matusik
Issue Date:July 2006
pp. 35-es
We present an algorithm and a system for high-quality natural video matting using a camera array. The system uses high frequencies present in natural scenes to compute mattes by creating a synthetic aperture image that is focused on the foreground object, ...
     
Natural video matting using camera arrays: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: Material presented at the ACM SIGGRAPH 2006 conference (SIGGRAPH '06)
By Neel Joshi, Shai Avidan, Wojciech Matusik
Issue Date:July 2006
pp. 35-es
We present an algorithm and a system for high-quality natural video matting using a camera array. The system uses high frequencies present in natural scenes to compute mattes by creating a synthetic aperture image that is focused on the foreground object, ...
     
Generalized spectral bounds for sparse LDA
Found in: Proceedings of the 23rd international conference on Machine learning (ICML '06)
By Baback Moghaddam, Shai Avidan, Yair Weiss
Issue Date:June 2006
pp. 641-648
We present a discrete spectral framework for the sparse or cardinality-constrained solution of a generalized Rayleigh quotient. This NP-hard combinatorial optimization problem is central to supervised learning tasks such as sparse LDA, feature selection an...
     
 1