Search For:

Displaying 1-27 out of 27 total
A Theory of Network Localization
Found in: IEEE Transactions on Mobile Computing
By James Aspnes, Tolga Eren, David K. Goldenberg, A. Stephen Morse, Walter Whiteley, Yang Richard Yang, Brian D.O. Anderson, Peter N. Belhumeur
Issue Date:December 2006
pp. 1663-1678
In this paper, we provide a theoretical foundation for the problem of network localization in which some nodes know their locations and other nodes determine their locations by measuring the distances to their neighbors. We construct grounded graphs to mod...
 
A Theory of Multiplexed Illumination
Found in: Computer Vision, IEEE International Conference on
By Yoav Y. Schechner, Shree K. Nayar, Peter N. Belhumeur
Issue Date:October 2003
pp. 808
Imaging of objects under variable lighting directions is an important and frequent practice in computer vision and image-based rendering. We introduce an approach that significantly improves the quality of such images. Traditional methods for acquiring ima...
 
Efficient Region Tracking With Parametric Models of Geometry and Illumination
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Gregory D. Hager, Peter N. Belhumeur
Issue Date:October 1998
pp. 1025-1039
<p><b>Abstract</b>—As an object moves through the field of view of a camera, the images of the object may change dramatically. This is not simply due to the translation of the object across the image plane. Rather, complications arise due...
 
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Peter N. Belhumeur, João P. Hespanha, David J. Kriegman
Issue Date:July 1997
pp. 711-720
<p><b>Abstract</b>—We develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as a coordinate i...
 
In Search of Illumination Invariants
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hansen F. Chen, Peter N. Belhumeur, David W. Jacobs
Issue Date:June 2000
pp. 1254
We consider the problem of determining functions of an image of an object that are insensitive to illumination changes. We first show that for an object with Lambertian reflectance there are no discriminative functions that are invariant to illumination. T...
 
Fusing with context: A Bayesian approach to combining descriptive attributes
Found in: Biometrics, International Joint Conference on
By Walter J. Scheirer,Neeraj Kumar,Karl Ricanek,Peter N. Belhumeur,Terrance E. Boult
Issue Date:October 2011
pp. 1-8
For identity related problems, descriptive attributes can take the form of any information that helps represent an individual, including age data, describable visual attributes, and contextual data. With a rich set of descriptive attributes, it is possible...
 
From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman
Issue Date:June 2001
pp. 643-660
<p><b>Abstract</b>—We present a generative appearance-based method for recognizing human faces under variation in lighting and viewpoint. Our method exploits the fact that the set of images of an object in fixed pose, but under all possib...
 
Color Subspaces as Photometric Invariants
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Todd Zickler, Satya P. Mallick, David J. Kriegman, Peter N. Belhumeur
Issue Date:June 2006
pp. 2000-2010
Complex reflectance phenomena such as specular reflections confound many vision problems since they produce image ?features? that do not correspond directly to intrinsic surface properties such as shape and spectral reflectance. A common approach to mitiga...
 
Time-Varying BRDFs
Found in: IEEE Transactions on Visualization and Computer Graphics
By Bo Sun, Kalyan Sunkavalli, Ravi Ramamoorthi, Peter N. Belhumeur, Shree K. Nayar
Issue Date:May 2007
pp. 595-609
<p><b>Abstract</b>—The properties of virtually all real-world materials change with time, causing their bidirectional reflectance distribution functions (BRDFs) to be time varying. However, none of the existing BRDF models and databases t...
 
Toward a Stratification of Helmholtz Stereopsis
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Todd E. Zickler, Peter N. Belhumeur, David J. Kriegman
Issue Date:June 2003
pp. 548
Helmholtz stereopsis has been previously introduced as a surface reconstruction technique that does not assume a model of surface reflectance. This technique relies on the use of multiple cameras and light sources, and it has been shown to be effective whe...
 
Image-based Modeling and Rendering of Surfaces with Arbitrary BRDFs
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Melissa L. Koudelka, Peter N. Belhumeur, Sebastian Magda, David J. Kriegman
Issue Date:December 2001
pp. 568
A goal of image-based rendering is to synthesize as realistically as possible man made and natural objects. This paper presents a method for image-based modeling and rendering of objects with arbitrary (possibly anisotropic and spatially varying) BRDFs. An...
 
From Few to Many: Generative Models for Recognition Under Variable Pose and Illumination
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman
Issue Date:March 2000
pp. 277
Image variability due to changes in pose and illumination can seriously impair object recognition. This paper presents appearance-based methods which, unlike previous appearance-based approaches, require only a small set of training images to generate a ri...
 
Illumination-Based Image Synthesis: Creating Novel Images of Human Faces Under Differing Pose and Lighting
Found in: Multi-View Modeling and Analysis of Visual Scenes, IEEE Workshop on
By Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman
Issue Date:June 1999
pp. 47
We present an illumination-based method for synthesizing images of an object under novel viewing conditions. Our method requires as few as three images of the object taken under variable illumination, but from a fixed viewpoint. Unlike multi-view based ima...
 
The Bas-Relief Ambiguity
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Peter N. Belhumeur, David J. Kriegman, Alan L. Yuille
Issue Date:June 1997
pp. 1060
Since antiquity, artisans have created flattened forms, often called ``bas-reliefs,'' which give an exaggerated perception of depth when viewed from a particular vantage point. This paper presents an explanation of this phenomena, showing that the ambiguit...
 
How Do You Tell a Blackbird from a Crow?
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Thomas Berg,Peter N. Belhumeur
Issue Date:December 2013
pp. 9-16
How do you tell a blackbird from a crow? There has been great progress toward automatic methods for visual recognition, including fine-grained visual categorization in which the classes to be distinguished are very similar. In a task such as bird species r...
 
Bird Part Localization Using Exemplar-Based Models with Enforced Pose and Subcategory Consistency
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jiongxin Liu,Peter N. Belhumeur
Issue Date:December 2013
pp. 2520-2527
In this paper, we propose a novel approach for bird part localization, targeting fine-grained categories with wide variations in appearance due to different poses (including aspect and orientation) and subcategories. As it is challenging to represent such ...
 
Localizing Parts of Faces Using a Consensus of Exemplars
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Peter N. Belhumeur,David W. Jacobs,David J. Kriegman,Neeraj Kumar
Issue Date:December 2013
pp. 2930-2940
We present a novel approach to localizing parts in images of human faces. The approach combines the output of local detectors with a nonparametric set of global models for the part locations based on over 1,000 hand-labeled exemplar images. By assuming tha...
 
Using Eye Reflections for Face Recognition Under Varying Illumination
Found in: Computer Vision, IEEE International Conference on
By Ko Nishino, Peter N. Belhumeur, Shree K. Nayar
Issue Date:October 2005
pp. 519-526
Face recognition under varying illumination remains a challenging problem. Much progress has been made toward a solution through methods that require multiple gallery images of each subject under varying illumination. Yet for many applications, this requir...
 
Beyond Lambert: Reconstructing Specular Surfaces Using Color
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Satya P. Mallick, Todd E. Zickler, David J. Kriegman, Peter N. Belhumeur
Issue Date:June 2005
pp. 619-626
We present a photometric stereo method for non-diffuse materials that does not require an explicit reflectance model or reference object. By computing a data-dependent rotation of RGB color space, we show that the specular reflection effects can be separat...
 
Merging Globally Rigid Formations of Mobile Autonomous Agents
Found in: Autonomous Agents and Multiagent Systems, International Joint Conference on
By Tolga Eren, Brian D.O. Anderson, Walter Whiteley, A. Stephen Morse, Peter N. Belhumeur
Issue Date:July 2004
pp. 1260-1261
This paper focuses on developing techniques and strategies for the analysis and design of sensor and network topologies required to merge globally rigid formations for cooperative tasks. Central to the development of these techniques and strategies is the ...
   
Making One Object Look Like Another: Controlling Appearance Using a Projector-Camera System
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Michael D. Grossberg, Harish Peri, Shree K. Nayar, Peter N. Belhumeur
Issue Date:July 2004
pp. 452-459
We present a method for controlling the appearance of an arbitrary 3D object using a projector and a camera. Our goal is to make one object look like another by projecting a carefully determined compensation image onto the object. The determination of the ...
 
Binocular Helmholtz Stereopsis
Found in: Computer Vision, IEEE International Conference on
By Todd E. Zickler, Jeffrey Ho, David J. Kriegman, Jean Ponce, Peter N. Belhumeur
Issue Date:October 2003
pp. 1411
Helmholtz stereopsis has been introduced recently as a surface reconstruction technique that does not assume a model of surface reflectance. In the reported formulation, correspondence was established using a rank constraint, necessitating at least three v...
 
Finding Folds: On the Appearance and Identification of Occlusion
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Patrick S. Huggins, Hansen F. Chen, Peter N. Belhumeur, Steven W. Zucker
Issue Date:December 2001
pp. 718
A natural sequel to edge detection is the interpretation of edges. This interpretation can provide useful information to various computer vision processes, including recognition, reconstruction, and tracking. In this paper we consider the problem of identi...
 
POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Thomas Berg,Peter N. Belhumeur
Issue Date:June 2013
pp. 955-962
From a set of images in a particular domain, labeled with part locations and class, we present a method to automatically learn a large and diverse set of highly discriminative intermediate features that we call Part-based One-vs.-One Features (POOFs). Each...
 
Beyond Lambert: Reconstructing Surfaces with Arbitrary BRDFs
Found in: Computer Vision, IEEE International Conference on
By Sebastian Magda, David J. Kriegman, Todd Zickler, Peter N. Belhumeur
Issue Date:July 2001
pp. 391
We address an open and hitherto neglected problem in computer vision, how to reconstruct the geometry of objects with arbitrary and possibly anisotropic bidirectional reflectance distribution functions (BRDFs). Present reconstruction techniques, whether st...
 
Active refocusing of images and videos
Found in: ACM Transactions on Graphics (TOG)
By Francesc Moreno-Noguer, Peter N. Belhumeur, Shree K. Nayar
Issue Date:July 2007
pp. 1-35
We present a system for refocusing images and videos of dynamic scenes using a novel, single-view depth estimation method. Our method for obtaining depth is based on the defocus of a sparse set of dots projected onto the scene. In contrast to other active ...
     
Lighting sensitive display
Found in: ACM Transactions on Graphics (TOG)
By Peter N. Belhumeur, Shree K. Nayar, Terry E. Boult
Issue Date:October 2004
pp. 963-979
Although display devices have been used for decades, they have functioned without taking into account the illumination of their environment. We present the concept of a lighting sensitive display (LSD)---a display that measures the incident illumination an...
     
 1