Search For:

Displaying 1-20 out of 20 total
Manifold bootstrapping for SVBRDF capture
Found in: ACM Transactions on Graphics (TOG)
By Baining Guo, Jiaping Wang, John Snyder, Moshe Ben-Ezra, Xin Tong, Yanxiang Lan, Yue Dong, Baining Guo, Jiaping Wang, John Snyder, Moshe Ben-Ezra, Xin Tong, Yanxiang Lan, Yue Dong, Baining Guo, Jiaping Wang, John Snyder, Moshe Ben-Ezra, Xin Tong, Yanxiang Lan, Yue Dong, Baining Guo, Jiaping Wang, John Snyder, Moshe Ben-Ezra, Xin Tong, Yanxiang Lan, Yue Dong
Issue Date:July 2010
pp. 1-10
Manifold bootstrapping is a new method for data-driven modeling of real-world, spatially-varying reflectance, based on the idea that reflectance over a given material sample forms a low-dimensional manifold. It provides a high-resolution result in both the...
     
High-resolution hyperspectral imaging via matrix factorization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By R. Kawakami,John Wright, Yu-Wing Tai,Yasuyuki Matsushita,Moshe Ben-Ezra,K. Ikeuchi
Issue Date:June 2011
pp. 2329-2336
Hyperspectral imaging is a promising tool for applications in geosensing, cultural heritage and beyond. However, compared to current RGB cameras, existing hyperspectral cameras are severely limited in spatial resolution. In this paper, we introduce a simpl...
 
Jitter Camera: High Resolution Video from a Low Resolution Detector
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Moshe Ben-Ezra, Assaf Zomet, Shree K. Nayar
Issue Date:July 2004
pp. 135-142
<p>Video cameras must produce images at a reasonable frame-rate and with a reasonable depth of field. These requirements impose fundamental physical limits on the spatial resolution of the image detector. As a result, current cameras produce videos w...
 
What Does Motion Reveal About Transparency?
Found in: Computer Vision, IEEE International Conference on
By Moshe Ben-Ezra, Shree K. Nayar
Issue Date:October 2003
pp. 1025
The perception of transparent objects from images is known to be a very hard problem in vision. Given a single image, it is difficult to even detect the presence of transparent objects in the scene. In this paper, we explore what can be said about transpar...
 
Motion Deblurring Using Hybrid Imaging
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Moshe Ben-Ezra, Shree K. Nayar
Issue Date:June 2003
pp. 657
Motion blur due to camera motion can significantly degrade the quality of an image. Since the path of the camera motion can be arbitrary, deblurring of motion blurred images is a hard problem. Previous methods to deal with this problem have included blind ...
 
Cameras for Stereo Panoramic Imaging
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shmuel Peleg, Yael Pritch, Moshe Ben-Ezra
Issue Date:June 2000
pp. 1208
A panorama for visual stereo consists of a pair of panoramic images, where one panorama is for the left eye, and another panorama is for the right eye. A panoramic stereo pair provides a stereo sensation up to a full 360 degrees. Two omni-directional camer...
 
Segmentation with Invisible Keying Signal
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Moshe Ben-Ezra
Issue Date:June 2000
pp. 1032
Chroma keying is the process of segmenting objects from images and video using color cues. A blue (or green) screen placed behind an object during recording is used in special effects and in virtual studios. A different background later replaces the blue c...
 
Automatic Disparity Control in Stereo Panoramas (OmniStereo)
Found in: Omnidirectional Vision, Workshop on
By Yael Pritch, Moshe Ben-Ezra, Shmuel Peleg
Issue Date:June 2000
pp. 54
An omnistereo panorama consists of a pair of panoramic images, where one panorama is for the left eye, and an-other panorama is for the right eye. An omnistereo pair provides a stereo sensation up to a full 360 degrees. OmniStereo panoramas can be created ...
 
Real-Time Motion Analysis with Linear-Programming
Found in: Computer Vision, IEEE International Conference on
By Moshe Ben-Ezra, Shmuel Peleg, Michael Werman
Issue Date:September 1999
pp. 703
A method to compute motion models in real time from point-to-line correspondences using linear programming is presented. Point-to-line correspondences are the most reliable motion measurements given the aperture effect, and it is shown how they can approxi...
 
Penrose Pixels for Super-Resolution
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Moshe Ben-Ezra, Zhouchen Lin, Bennett Wilburn, Wei Zhang
Issue Date:July 2011
pp. 1370-1383
We present a novel approach to reconstruction-based super-resolution that uses aperiodic pixel tilings, such as a Penrose tiling or a biological retina, for improved performance. To this aim, we develop a new variant of the well-known error back projection...
 
Video Super-Resolution Using Controlled Subpixel Detector Shifts
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Moshe Ben-Ezra, Assaf Zomet, Shree K. Nayar
Issue Date:June 2005
pp. 977-987
Video cameras must produce images at a reasonable frame-rate and with a reasonable depth of field. These requirements impose fundamental physical limits on the spatial resolution of the image detector. As a result, current cameras produce videos with a ver...
 
A framework for ultra high resolution 3D imaging
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Zheng Lu, Yu-Wing Tai, Moshe Ben-Ezra, Michael S. Brown
Issue Date:June 2010
pp. 1205-1212
We present an imaging framework to acquire 3D surface scans at ultra high-resolutions (exceeding 600 samples per mm<sup>2</sup>). Our approach couples a standard structured-light setup and photometric stereo using a large-format ultra-high-reso...
 
An LED-only BRDF measurement device
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Moshe Ben-Ezra, Jiaping Wang, Bennett Wilburn, Xiaoyang Li, Le Ma
Issue Date:June 2008
pp. 1-8
Light Emitting Diodes (LEDs) can be used as light detectors and as light emitters. In this paper, we present a novel BRDF measurement device consisting exclusively of LEDs. Our design can acquire BRDFs over a full hemisphere, or even a full sphere (for the...
 
Penrose Pixels Super-Resolution in the Detector Layout Domain
Found in: Computer Vision, IEEE International Conference on
By Moshe Ben-Ezra, Zhouchen Lin, Bennett Wilburn
Issue Date:October 2007
pp. 1-8
We present a novel approach to reconstruction based super-resolution that explicitly models the detector's pixel layout. Pixels in our model can vary in shape and size, and there may be gaps between adjacent pixels. Furthermore, their layout can be periodi...
 
Motion-Based Motion Deblurring
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Moshe Ben-Ezra, Shree K. Nayar
Issue Date:June 2004
pp. 689-698
<p><b>Abstract</b>—Motion blur due to camera motion can significantly degrade the quality of an image. Since the path of the camera motion can be arbitrary, deblurring of motion blurred images is a hard problem. Previous methods to deal w...
 
Omnistereo: Panoramic Stereo Imaging
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Shmuel Peleg, Moshe Ben-Ezra, Yael Pritch
Issue Date:March 2001
pp. 279-290
<p><b>Abstract</b>—An Omnistereo panorama consists of a pair of panoramic images, where one panorama is for the left eye and another panorama is for the right eye. The panoramic stereo pair provides a stereo sensation up to a full 360 deg...
 
Stereo Panorama with a Single Camera
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shmuel Peleg, Moshe Ben-Ezra
Issue Date:June 1999
pp. 1395
Full panoramic images, covering 360 degrees, can be created either by using panoramic cameras or by mosaicing together many regular images. Creating panoramic views in stereo, where one panorama is generated for the left eye, and another panorama is genera...
 
Efficient Computation of the Most Probable Motion from Fuzzy Correspondences
Found in: Applications of Computer Vision, IEEE Workshop on
By Moshe Ben-Ezra, Shmuel Peleg, Michael Werman
Issue Date:October 1998
pp. 22
An algorithm is presented for finding the most probable image motion between two images from fuzzy point correspondences. In fuzzy correspondence a point in one image is assigned to a region in the other image. Such a region can be line (aperture effect) o...
 
Imaging buddhist art with a digital large-format camera: A field study report from the dunhuang caves
Found in: Journal on Computing and Cultural Heritage (JOCCH)
By Michael S. Brown, Moshe Ben-Ezra, Wei Luo, Zheng Lu, Zhijun Sun
Issue Date:October 2012
pp. 1-10
This article describes recent field work undertaken by Microsoft Research Asia and the Dunhuang Academy to capture high-resolution images of Buddhist art at the UNESCO world heritage site, the Mogao Caves. This project is intended as a feasibility study ex...
     
Manifold bootstrapping for SVBRDF capture
Found in: ACM SIGGRAPH 2010 papers (SIGGRAPH '10)
By Baining Guo, Jiaping Wang, John Snyder, Moshe Ben-Ezra, Xin Tong, Yanxiang Lan, Yue Dong
Issue Date:July 2010
pp. 10-18
Manifold bootstrapping is a new method for data-driven modeling of real-world, spatially-varying reflectance, based on the idea that reflectance over a given material sample forms a low-dimensional manifold. It provides a high-resolution result in both the...
     
 1