Search For:

Displaying 1-32 out of 32 total
Space-Time Super-Resolution
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Eli Shechtman, Yaron Caspi, Michal Irani
Issue Date:April 2005
pp. 531-545
We propose a method for constructing a video sequence of high space-time resolution by combining information from multiple low-resolution video sequences of the same dynamic scene. Super-resolution is performed simultaneously in time and in space. By
 
Co-segmentation by Composition
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Alon Faktor,Michal Irani
Issue Date:December 2013
pp. 1297-1304
Given a set of images which share an object from the same semantic category, we would like to co-segment the shared object. We define 'good' co-segments to be ones which can be easily composed (like a puzzle) from large pieces of other co-segments, yet are...
 
Nonparametric Blind Super-resolution
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Tomer Michaeli,Michal Irani
Issue Date:December 2013
pp. 945-952
Super resolution (SR) algorithms typically assume that the blur kernel is known (either the Point Spread Function 'PSF' of the camera, or some default low-pass filter, e.g. a Gaussian). However, the performance of SR methods significantly deteriorates when...
 
Detecting and sketching the common
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shai Bagon, Ori Brostovski, Meirav Galun, Michal Irani
Issue Date:June 2010
pp. 33-40
Given very few images containing a common object of interest under severe variations in appearance, we detect the common object and provide a compact visual representation of that object, depicted by a binary sketch. Our algorithm is composed of two stages...
 
Regenerative morphing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Eli Shechtman, Alex Rav-Acha, Michal Irani, Steve Seitz
Issue Date:June 2010
pp. 615-622
We present a new image morphing approach in which the output sequence is regenerated from small pieces of the two source (input) images. The approach does not require manual correspondence, and generates compelling results even when the images are of very ...
 
Summarizing visual data using bidirectional similarity
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Denis Simakov, Yaron Caspi, Eli Shechtman, Michal Irani
Issue Date:June 2008
pp. 1-8
We propose a principled approach to summarization of visual data (images or video) based on optimization of a well-defined similarity measure. The problem we consider is re-targeting (or summarization) of image/video data into smaller sizes. A good “visual...
 
In defense of Nearest-Neighbor based image classification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Oren Boiman, Eli Shechtman, Michal Irani
Issue Date:June 2008
pp. 1-8
State-of-the-art image classification methods require an intensive learning/training stage (using SVM, Boosting, etc.) In contrast, non-parametric Nearest-Neighbor (NN) based image classifiers require no training time and have other favorable properties. H...
 
Actions as Space-Time Shapes
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Lena Gorelick, Moshe Blank, Eli Shechtman, Michal Irani, Ronen Basri
Issue Date:December 2007
pp. 2247-2253
Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as three- imensional shapes induced by the silhouettes in the spacetime volume. We adopt a recent appro...
 
Space-Time Behavior-Based Correlation—OR—How to Tell If Two Underlying Motion Fields Are Similar Without Computing Them?
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Eli Shechtman, Michal Irani
Issue Date:November 2007
pp. 2045-2056
We introduce a behavior-based similarity measure which tells us whether two different space-time intensity patterns of two different video segments could have resulted from a similar underlying motion field. This is done directly from the intensity informa...
 
Matching Local Self-Similarities across Images and Videos
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Eli Shechtman, Michal Irani
Issue Date:June 2007
pp. 1-8
We present an approach for measuring similarity between visual entities (images or videos) based on matching internal self-similarities. What is correlated across images (or across video sequences) is the internal layout of local self-similarities (up to s...
 
Space-Time Completion of Video
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yonatan Wexler, Eli Shechtman, Michal Irani
Issue Date:March 2007
pp. 463-476
This paper presents a new framework for the completion of missing information based on local structures. It poses the task of completion as a global optimization problem with a well-defined objective function and derives a new algorithm to optimize it. Mis...
 
Detecting Irregularities in Images and in Video
Found in: Computer Vision, IEEE International Conference on
By Oren Boiman, Michal Irani
Issue Date:October 2005
pp. 462-469
We address the problem of detecting irregularities in visual data, e.g., detecting suspicious behaviors in video sequences, or identifying salient patterns in images. The term
 
Separating Transparent Layers of Repetitive Dynamic Behaviors
Found in: Computer Vision, IEEE International Conference on
By Bernard Sarel, Michal Irani
Issue Date:October 2005
pp. 26-32
In this paper we present an approach for separating two transparent layers of complex non-rigid scene dynamics. The dynamics in one of the layers is assumed to be repetitive, while the other can have any arbitrary dynamics. Such repetitive dynamics include...
 
Actions as Space-Time Shapes
Found in: Computer Vision, IEEE International Conference on
By Moshe Blank, Lena Gorelick, Eli Shechtman, Michal Irani, Ronen Basri
Issue Date:October 2005
pp. 1395-1402
Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as three-dimensional shapes induced by the silhouettes in the space-time volume. We adopt a recent appr...
 
Space-Time Behavior Based Correlation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Eli Shechtman, Michal Irani
Issue Date:June 2005
pp. 405-412
<p>We introduce a behavior-based similarity measure which tells us whether two different space-time intensity patterns of two different video segments could have resulted from a similar underlying motion field. This is done directly from the intensit...
 
Degeneracies, Dependencies and their Implications in Multi-body and Multi-Sequence Factorizations
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lihi Zelnik-Manor, Michal Irani
Issue Date:June 2003
pp. 287
The body of work on multi-body factorization separates between objects whose motions are independent. In this work we show that in many cases objects moving with different 3D motions will be captured as a single object using these approaches. We analyze wh...
 
Spatio-Temporal Alignment of Sequences
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yaron Caspi, Michal Irani
Issue Date:November 2002
pp. 1409-1424
<p><b>Abstract</b>—This paper studies the problem of sequence-to-sequence alignment, namely, establishing correspondences in <it>time</it> and in <it>space</it> between two different video sequences of the same dyn...
 
Direct Recovery of Planar-Parallax from Multiple Frames
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Michal Irani, P. Anandan, Meir Cohen
Issue Date:November 2002
pp. 1528-1534
<p><b>Abstract</b>—In this paper, we present an algorithm that estimates dense planar-parallax motion from <it>multiple uncalibrated</it> views of a 3D scene. This generalizes the
 
Multiview Constraints on Homographies
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Lihi Zelnik-Manor, Michal Irani
Issue Date:February 2002
pp. 214-223
<p><b>Abstract</b>—The image motion of a planar surface between two camera views is captured by a homography (a <tmath>2D</tmath> projective transformation). The homography depends on the intrinsic and extrinsic camera paramet...
 
Event-Based Analysis of Video
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lihi Zelnik-Manor, Michal Irani
Issue Date:December 2001
pp. 123
Dynamic events can be regarded as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple statistical distance measure between video sequences (possibly of different len...
 
Alignment of Non-Overlapping Sequences
Found in: Computer Vision, IEEE International Conference on
By Yaron Caspi, Michal Irani
Issue Date:July 2001
pp. 76
This paper shows how two image sequences that have no spatial overlap between their fields of view can be aligned both in time and in space. Such alignment is possible when the two cameras are attached closely together and are moved jointly in space. The c...
 
A Step towards Sequence-to-Sequence Alignment
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yaron Caspi, Michal Irani
Issue Date:June 2000
pp. 2682
This paper presents an approach for establishing correspondences in time and in space between two different video sequences of the same dynamic scene, recorded by stationary uncalibrated video cameras. The method simultaneously estimates both spatial align...
 
Multi-View Subspace Constraints on Homographies
Found in: Computer Vision, IEEE International Conference on
By Lihi Zelnik-Manor, Michal Irani
Issue Date:September 1999
pp. 710
The motion of a planar surface between two camera views induces a homography. The homography depends on the camera intrinsic and extrinsic parameters, as well as on the 3D plane parameters. While camera parameters vary across different views, the plane geo...
 
Multi-Frame Alignment of Planes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lihi Zelnik-Manor, Michal Irani
Issue Date:June 1999
pp. 1151
Traditional plane alignment techniques are typically performed between pairs of frames. In this paper we present a method for extending existing two-frame planar-motion estimation techniques into a simultaneous multi-frame estimation, by exploiting multi-f...
 
A Unified Approach to Moving Object Detection in 2D and 3D Scenes
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Michal Irani, P. Anandan
Issue Date:June 1998
pp. 577-589
<p><b>Abstract</b>—The detection of moving objects is important in many tasks. Previous approaches to this problem can be broadly divided into two classes: 2D algorithms which apply when the scene can be approximated by a flat surface and...
 
Recovery of Ego-Motion Using Region Alignment
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Michal Irani, Benny Rousso, Shmuel Peleg
Issue Date:March 1997
pp. 268-272
<p><b>Abstract</b>—A method for computing the 3D camera motion (the <it>ego-motion</it>) in a static scene is described, where initially a detected 2D motion between two frames is used to align corresponding image regions. We ...
 
Representation of Scenes from Collections of Images
Found in: Representation of Visual Scenes, IEEE Workshop on
By Rakesh Kumar, P. Anandan, michal Irani, James Bergen, Keith Hanna
Issue Date:June 1995
pp. 10
The goal of computer vision is to extract information about the world from collections of images. This information might be used to recognize or manipulate objects, to control movement through the environment, to measure or determine the condition of objec...
 
"Clustering by Composition" - Unsupervised Discovery of Image Categories
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Alon Faktor,Michal Irani
Issue Date:December 2013
pp. 1
We define a "good image cluster" as one in which images can be easily composed (like a puzzle) using pieces from each other, while are difficult to compose from images outside the cluster. The larger and more statistically significant the pieces ...
 
Separating Signal from Noise Using Patch Recurrence across Scales
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Maria Zontak,Inbar Mosseri,Michal Irani
Issue Date:June 2013
pp. 1195-1202
Recurrence of small clean image patches across different scales of a natural image has been successfully used for solving ill-posed problems in clean images (e.g., super-resolution from a single image). In this paper we show how this multi-scale property c...
 
Combining the power of Internal and External denoising
Found in: 2013 IEEE International Conference on Computational Photography (ICCP)
By Inbar Mosseri,Maria Zontak,Michal Irani
Issue Date:April 2013
pp. 1-9
Image denoising methods can broadly be classified into two types: “Internal Denoising” (denoising an image patch using other noisy patches within the noisy image), and “External Denoising” (denoising a patch using external clean natural image patches). Any...
   
Multi-Frame Estimation of Planar Motion
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Lihi Zelnik-Manor, Michal Irani
Issue Date:October 2000
pp. 1105-1116
<p><b>Abstract</b>—Traditional plane alignment techniques are typically performed between <it>pairs</it> of frames. In this paper, we present a method for extending existing two-frame planar motion estimation techniques into a...
 
Robust Multi-Sensor Image Alignment
Found in: Computer Vision, IEEE International Conference on
By Michal Irani, P. Anandan
Issue Date:January 1998
pp. 959
<p>This paper presents a method for alignment of images acquired by sensors of different modalities (e.g., EO and IR). The paper has two main contributions: (i) It identifies an appropriate image representation for multi-sensor alignment, i.e., a rep...
 
 1