Peter N. Belhumeur

P.: Color subspaces as photometric invariants (2009)

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...

Todd Zickler, Satya P. Mallick, David J. Kriegman, Peter N. Belhumeur

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...

Using Eye Reflections for Face Recognition Under Varying Illumination (2009)

Ko Nishino, Peter N. Belhumeur, Shree K. Nayar

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...

Searching the World’s Herbaria: A System for Visual Identification of Plant Species (2009)

Peter N. Belhumeur, Daozheng Chen, Steven Feiner, David W. Jacobs, W. John Kress, Haibin Ling, ...

Abstract. We describe a working computer vision system that aids in the identification of plant species. A user photographs an isolated leaf on a blank background, and the system extracts the leaf...

IEEE Comparing Images Under Variable Illumination (2009)

David W. Jacobs, Peter N. Belhumeur, Ronen Basri

We consider the problem of determining whether two images come from different objects or the same object in the same pose, but under different illumination conditions. We show that this problem...

Bo Sun, Student Member, IEEE Computer Society, Kalyan Sunkavalli, (2008)

Time-varying Brdfs, Ravi Ramamoorthi, Peter N. Belhumeur, Shree K. Nayar

Abstract—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...

Abstract (2008)

Todd Zickler, David J. Kriegman, Peter N. Belhumeur

We present a method – termed Helmholtz stereopsis – for reconstructing the geometry of objects from a collection of images. Unlike existing methods for surface reconstruction (e.g., stereo...

15th Triennial World Congress, Barcelona, Spain A FRAMEWORK FOR MAINTAINING FORMATIONS BASED ON RIGIDITY (2008)

Tolga Eren, Peter N. Belhumeur

Abstract: In this paper, a framework for maintaining formations of large number of mobile autonomous vehicles based on rigidity is proposed. The aim of this paper is to explore strategies for...

A Theory of Multiplexed Illumination (2008)

Peter N. Belhumeur

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...

In the Proceedings of CVPR97. The Bas-Relief Ambiguity (2008)

Peter N. Belhumeur, David J. Kriegman, Alan L. Yuille

Since antiquity, artisans have created attened forms, often called \bas-reliefs, " which give an exaggerated perception of depth when viewed from a particular vantage point. This paper...

Using Eye Reflections for Face Recognition Under Varying Illumination (2008)

Ko Nishino, Peter N. Belhumeur, Shree K. Nayar

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...

Under Variable Lighting: Faces (2008)

Athinodoros S. Georghiades, David J. Kriegman, Peter N. Belhumeur

Objective function (2008)

Appeared in the IEEE Conf. on Computer Vision and Pattern Recognition 1992. A Bayesian Treatment of the Stereo Correspondence Problem Using Half-Occluded Regions (2008)

The tracking problem We want to keep track of the interesting object or region in a video sequence. Intrinsic difficulties • movements in 3D • illumination changes • shape changes (deformation)...

Peter N. Belhumeur, David Mumford

A half-occluded region in a stereo pair is a set of pixels in one image representing points in space visible to that camera or eye only, and not to the other. These occur typically as parts of the...

Submitted to SIGGRAPH 2001 Image-based Modeling and Rendering of Surfaces with Arbitrary BRDFs Abstract (2008)

Melissa Koudelka, Sebastian Magda, Peter N. Belhumeur, David J. Kriegman

A challenge of computer graphics is to render as realistically as possible manmade and natural objects. This paper presents a method for image-based modeling and rendering of objects with arbitrary...

Displays h... (2008)

Color Subspaces as Photometric Invariants (2008)

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...

Todd Zickler, Satya P. Mallick, David J. Kriegman, Peter N. Belhumeur

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...

z (2007)

Peter N. Belhumeur, David J. Kriegman, Alan L. Yuille

When an unknown object with Lambertian reflectance is viewed orthographically, there is an implicit ambiguity in determining its 3-d structure: we show that the object's visible surface f(x; y)...

Multiplexing for optimal lighting (2007)

Yoav Y. Schechner, Shree K. Nayar, Peter N. Belhumeur

Abstract—Imaging of objects under variable lighting directions is an important and frequent practice in computer vision, machine vision, and image-based rendering. Methods for such imaging have...

Reflectance Sharing: Predicting Appearance from a Sparse Set of Images of a Known Shape (2007)

Todd Zickler, Ravi Ramamoorthi, Sebastian Enrique, Peter N. Belhumeur

Three-dimensional appearance models consisting of spatially-varying reflectance functions defined on a known shape can be used in analysis-by-synthesis approaches to a number of visual tasks. The...

Reflectance Sharing: Predicting Appearance from a Sparse Set of Images of a Known Shape (2007)

Todd Zickler, Ravi Ramamoorthi, Sebastian Enrique, Peter N. Belhumeur

Abstract—Three-dimensional appearance models consisting of spatially varying reflectance functions defined on a known shape can be used in analysis-by-synthesis approaches to a number of visual...

Reflectance Sharing: Predicting Appearance from a Sparse Set of Images of a Known Shape (2007)

Todd Zickler, Ravi Ramamoorthi, Sebastian Enrique, Peter N. Belhumeur

Abstract—Three-dimensional appearance models consisting of spatially varying reflectance functions defined on a known shape can be used in analysis-by-synthesis approaches to a number of visual...

A First Order Analysis of Lighting, Shading, and Shadows (2006)

Ramamoorthi, Ravi, Mahajan, Dhruv, Belhumeur, Peter N.

The shading in a scene depends on a combination of many factors---how the lighting varies spatially across a surface, how it varies along different directions, the geometric curvature and reflectance...

Using Angle of Arrival (Bearing) Information in Network Localization (2006)

Rigid Formations with Leader-Follower Architecture (2006)

In this paper, we consider using angle of arrival information (bearing) for network localization and control in two different fields of multi-agent systems: (i) wireless sensor networks; (ii) robot...

A theory of network localization (2006)

This paper is concerned with information structures used in rigid formations of autonomous agents that have leader-follower architecture. The focus of the paper is on sensor/network topologies to...

James Aspnes, Tolga Eren, David K. Goldenberg, Student Member, A. Stephen Morse, Walter Whiteley, ...

Abstract—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...

Specularity removal in images and videos: A PDE approach (2006)

Satya P. Mallick, Todd Zickler, Peter N. Belhumeur, David J. Kriegman

Abstract. We present a unified framework for separating specular and diffuse reflection components in images and videos of textured scenes. This can be used for specularity removal and for...

Graphical Properties of Easily Localizable Sensor Networks (2006)

Peter N Belhumeur, Tolga Eren, David K Goldenberg, A Stephen, Morse Walter Whiteley, ...

The sensor network localization problem is one of determining the Euclidean positions of all sensors in a network given knowledge of the Euclidean positions of some, and knowledge of a number of...

Specularity removal in images and videos: A PDE approach (2006)

Satya P. Mallick, Todd Zickler, Peter N. Belhumeur, David J. Kriegman

Abstract. We present a unified framework for separating specular and diffuse reflection components in images and videos of textured scenes. This can be used for specularity removal and for...

Time-Varying Textures (2005)

Enrique, Sebastian, Koudelka, Melissa, Belhumeur, Peter N., Dorsey, Julie, Nayar, Shree, Ramamoorthi, Ravi

Essentially all computer graphics rendering assumes that the reflectance and texture of surfaces is a static phenomenon. Yet, there is an abundance of materials in nature whose appearance varies...

Merging Globally Rigid Formations of Mobile Autonomous Agents (2005)

Eren, Tolga, Anderson, Brian, Whiteley, Walter, Morse, A. Stephen, Belhumeur, Peter N.

This paper is concerned with merging globally rigid formations of mobile autonomous agents. A key element in all future multi-agent systems will be the role of sensor and communication networks as an...

Rigid Formations with Leader-Follower Architecture (2005)

Information structures to secure control of rigid formations with leader-follower structure (2005)

This paper is concerned with information structures used in rigid formations of autonomous agents that have leader-follower architecture. The focus of this paper is on sensor/network topologies to...

Tolga Eren, Walter Whiteley, A. Stephen Morse, Peter N. Belhumeur

Abstract — This paper is concerned with rigid formations of mobile autonomous agents using a leader-follower structure. A formation is a group of agents moving in real 2- or 3dimensional space. A...

Information structures to secure control of rigid formations with leader-follower structure (2005)

Tolga Eren, Walter Whiteley, A. Stephen Morse, Peter N. Belhumeur

Abstract — This paper is concerned with rigid formations of mobile autonomous agents that have leader-follower architecture. In a previous paper, Baillieul and Suri gave a proposition as a...

P.: Further results on sensor network localization using rigidity (2005)

P.: Further results on sensor network localization using rigidity (2005)

Abstract — Two further results, which extend the previous work on the use of rigidity in sensor network localization, are given. The previous work provided the conditions for the localization of an...

Rigid formations with leader-follower architecture (2005)

Abstract-Two further results, which extend the previous work on the use of rigidity in sensor network localization, are given, The previous work provided the conditions for the localization of an...

Optimal illumination for image and video relighting (2005)

Abstract — This paper is concerned with information structures used in rigid formations of autonomous agents that have leaderfollower architecture. The focus of this paper is on sensor/network...

Francesc Moreno-noguer, Shree K. Nayar, Peter N. Belhumeur

rendering, Lighting representation It has been shown in the literature that image-based relighting of scenes with unknown geometry can be achieved through linear combinations of a set of pre-acquired...

Information Structures to Secure Control of Rigid Formations with Leader-Follower Structure (2004)

Eren, Tolga, Whiteley, Walter, Anderson, Brian D.O., Morse, A. Stephen, Belhumeur, Peter N.

This paper is concerned with rigid formations of mobile autonomous agents using a leader-follower structure. A formation is a group of agents moving in real 2- or 3- dimensional space. A formation is...

A Theoretical Analysis of the Conditions for Unambiguous Node Localization in Sensor Networks (2004)

Lighting sensitive display (2004)

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 distances or...

A theoretical analysis of the conditions for unambiguous node localization in sensor networks (2004)

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...

Information structures to secure control of globally rigid formations (2004)

Abstract — 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...

Tolga Eren, Walter Whiteley, A. Stephen, Morse Brian, D. O. Anderson, Peter N. Belhumeur

Abstract — Sensor and network topologies of rigid formations with distance information between mobile autonomous agents are considered. An approach based on rigidity for creating such topologies...

Merging globally rigid formations of mobile autonomous agents (2004)

Tolga Eren, Walter Whiteley, A. Stephen Morse, Peter N. Belhumeur

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...

Making One Object Look Like Another: Controlling Appearance using a Projector-Camera System (2004)

Michael D. Grossberg, Harish Peri, Shree K. Nayar, Peter N. Belhumeur

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...

Lighting sensitive display (2004)

Operations on Rigid Formations of Autonomous Agents (2003)

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...

Anderson, Brian D. O., Belhumeur, Peter N., Eren, Tolga, Morse, A. Stephen, Whiteley, Walter

This paper is concerned with the maintenance of rigid formations of mobile autonomous agents. A key element in all future multi-agent systems will be the role of sensor and communication networks as...

Toward a Stratification of Helmholtz Stereopsis (2003)

Todd E. Zickler, Peter N. Belhumeur

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...

Acquisition, compression, and synthesis of bidirectional texture functions (2003)

Melissa L. Koudelka, Sebastian Magda, Peter N. Belhumeur, David J. Kriegman

Abstract — Real world surfaces such as tree bark, moss, sponge, and fur often have complicated geometry that leads to effects such as self-shadowing, masking, specularity, and interreflection as...

A projection system with radiometric compensation for screen imperfections (2003)

Shree K. Nayar, Harish Peri, Michael D. Grossberg, Peter N. Belhumeur

A major limitation of existing projection display systems is that they rely on a high quality screen for projecting images. We believe that relaxing this restriction will make projectors more useful...

Toward a Stratification of Helmholtz Stereopsis (2003)

Todd E. Zickler, Peter N. Belhumeur, David J. Kriegman

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...

Helmholtz Stereopsis: Exploiting Reciprocity for Surface Reconstruction (2002)

Todd Zickler, Peter N. Belhumeur, David J. Kriegman

Abstract. We present a method – termed Helmholtz stereopsis – for reconstructing the geometry of objects from a collection of images. Unlike most existing methods for surface reconstruction...

Closing Ranks in Vehicle Formations Based on Rigidity (2002)

Tolga Eren, Peter N. Belhumeur, A. Stephen Morse

In this paper, a systematic way of maintaining rigidity in case of vehicle removals in formations for coordinating mobile autonomous vehicles with limited communication/sensing links is presented....

Closing Ranks In Vehicle Formations Based On Rigidity (2002)

Tolga Eren, Peter N. Belhumeur, A. Stephen Morse

This paper addresses the closing ranks problem in formations of coordinating large number of autonomous vehicles with limited communication /sensing requirements. We propose a framework based on...

A Framework For Maintaining Formations Based On Rigidity (2002)

Tolga Eren, Peter N. Belhumeur

In this paper, a framework for maintaining formations of large number of mobile autonomous vehicles based on rigidity is proposed. The aim of this paper is to explore strategies for maintaining...

A Framework For Maintaining Formations Based On Rigidity (2002)

Tolga Eren, Peter N. Belhumeur, A. Stephen Morse

In this paper, a framework for maintaining formations of large number of mobile autonomous vehicles based on rigidity is proposed. The aim of this paper is to explore strategies for maintaining...

A framework for maintaining formations based on rigidity (2002)

Tolga Eren, Peter N. Belhumeur

Abstract: In this paper, a framework for maintaining formations of large number of mobile autonomous vehicles based on rigidity is proposed. The aim of this paper is to explore strategies for...

Helmholtz Stereopsis: Exploiting Reciprocity for Surface Reconstruction, ECCV (2002)

Todd Zickler, Peter N. Belhumeur, David J. Kriegman

Abstract. We present a method – termed Helmholtz stereopsis – for reconstructing the geometry of objects from a collection of images. Unlike most existing methods for surface reconstruction...

From Few to many: Illumination cone models for face recognition under variable lighting and pose (2001)

Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman

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,...

Image-based Modeling and Rendering of Surfaces with Arbitrary BRDFs (2001)

Melissa L. Koudelka, Peter N. Belhumeur, Sebastian Magda, David J. Kriegman

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...

From Few to many: Illumination cone models for face recognition under variable lighting and pose (2001)

Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman

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,...

From few to many: Illumination cone models for face recognition under variable lighting and pose (2001)

Athinodoros S. Georghiades, Student Member, Peter N. Belhumeur, David J. Kriegman, Senior Member

AbstractÐWe 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...

c ○ 2002 Kluwer Academic Publishers. Manufactured in The Netherlands. Helmholtz Stereopsis: Exploiting Reciprocity for Surface Reconstruction (2001)

Todd E. Zickler, Peter N. Belhumeur, David J. Kriegman

Abstract. We present a method—termed Helmholtz stereopsis—for reconstructing the geometry of objects from a collection of images. Unlike existing methods for surface reconstruction (e.g., stereo...

From Few to Many: Generative Models for Recognition Under Variable Pose and Illumination (2000)

Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman

Abstract 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...

From Few to Many: Generative Models for Recognition Under Variable Pose and Illumination (2000)

Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman

Abstract 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...

From Few to Many: Generative Models for Recognition Under Variable Pose and Illumination (2000)

Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman

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,...

From Few to Many: Generative Models for Recognition Under Variable Pose and Illumination (2000)

Athinodoros Georghiades Peter, Peter N. Belhumeur, David J. Kriegman

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,...

In search of illumination invariants (2000)

Hansen F. Chen, Peter N. Belhumeur, David W. Jacobs

We consider the problem of determining functions of an image of an object that are insensitive to illumination changes. We rst show that for an object with Lambertian re ectance there are no...

In search of illumination invariants (2000)

Hansen F. Chen, Peter N. Belhumeur, David W. Jacobs

We consider the problem of determining functions of an image of an object that are insensitive to illumination changes. We rst show that for an object with Lambertian re ectance there are no...

From Few to Many: Generative Models for Recognition Under Variable Pose and Illumination (2000)

Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman

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,...

The bas-relief ambiguity (1999)

Peter N. Belhumeur, David J. Kriegman, Alan L. Yuille

When an unknown object with Lambertian re ectance isviewed orthographically, there is an implicit ambiguity in determining its 3-d structure: we show that the object's visible surface f(x � y)...

Illumination-Based Image Synthesis: Creating Novel Images of Human Faces Under Differing Pose and Lighting (1999)

A. S. Georghiades, Peter N. Belhumeur, David J. Kriegman

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...

Shape and Enlightenment: Reconstruction and Recognition under Variable Illumination (1999)

David J. Kriegman, Peter N. Belhumeur, Athinodoros S. Georghiades

Due to illumination variability, the same object can appear dramatically different even when viewed in fixed pose, and this variability can confound recognition systems. This paper summarizes recent...

The Bas-Relief Ambiguity (1999)

Peter N. Belhumeur, David J. Kriegman, Alan L. Yuille

When an unknown object with Lambertian reflectance is viewed orthographically, there is an implicit ambiguity in determining its 3-d structure: we show that the object's visible surface is...

T echnicalReport on Illumination Invariance (1999)

Hansen F. Chen, Peter N. Belhumeur, David W. Jacobs

We consider the problem of determining functions of an image of an obje ct that are insensitive to illumination changes. We rst show that for an object with Lambertian r e e ctanc e ther eareno...

c ○ 1999 Kluwer Academic Publishers. Manufactured in The Netherlands. Computational Vision at Yale (1999)

Peter N. Belhumeur, James S. Duncan, Gregory D. Hager, A. Stephen Morse, Steven W. Zucker

Abstract. We present a brief introduction to the five articles that make up this special issue: Shock Graphs and

Illumination-based image synthesis: Creating novel images of human faces under differing pose and lighting (1999)

Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman

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...

What shadows reveal about object structure (1998)

David J. Kriegman, Peter N. Belhumeur

Abstract. In a scene observed from a xed viewpoint, the set of shadow curves in an image changes as a point light source (nearby or at in nity) assumes di erent locations. We show that for any nite...

Efficient region tracking with parametric models of geometry and illumination (1998)

Efficient region tracking with parametric models of geometry and illumination (1998)

Abstract—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....

What Shadows Reveal about Object Structure (1998)

Abstract---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....

David J. Kriegman, Peter N. Belhumeur

In a scene observed from a fixed viewpoint, the set of shadow curves in an image changes as a point light source (nearby or at infinity) assumes different locations. We show that for any finite set...

Illumination Cones for Recognition Under Variable Lighting: Faces (1998)

Athinodoros S. Georghiades, David J. Kriegman, Peter N. Belhumeur

Due to illumination variability, the same object can appear dramatically different even when viewed in fixed pose. To handle this variability, an object recognition system must employ a...

Efficient Region Tracking With Parametric Models of Geometry and Illumination (1998)

What Is the Set of Images of an Object under All Possible Illumination Conditions? (1998)

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,...

Peter N. Belhumeur, David J. Kriegman

The appearance of an object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for any pose...

What Is The Set Of Images Of An Object Under All Possible Lighting Conditions (1998)

Peter N. Belhumeur, David J. Kriegman

The appearance of a particular object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for...

Efficient region tracking with parametric models of geometry and illumination (1998)

Illumination cones for recognition under variable lighting: Faces (1998)

Abstract—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....

Athinodoros S. Georghiades, David J. Kriegman, Peter N. Belhumeur

Due to illumination variability, the same object can appear dramatically di erent even when viewed in xed pose. To handle this variability, an object recognition system must employ a representation...

Illumination cones for recognition under variable lighting: Faces (1998)

Athinodoros S. Georghiades, David J. Kriegman, Peter N. Belhumeur

Due to illumination variability, the same object can appear dramatically di erent even when viewed in xed pose. To handle this variability, an object recognition system must employ a representation...

Comparing images under variable illumination (1998)

David W. Jacobs, Peter N. Belhumeur, Ronen Basri

We consider the problem of determining whether two images come from different objects or the same object in the same pose, but under different illumination conditions. We show that this problem...

What shadows reveal about object structure (1998)

David J. Kriegman, Peter N. Belhumeur

In a scene observed from a fixed viewpoint, the set of shadow boundaries in an image changes as a point light source (nearby or at infinity) assumes different locations. We show that for any finite...

Efficient region tracking with parametric models of geometry and illumination (1998)

The Bas-Relief Ambiguity (1997)

Abstract—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....

Peter N. Belhumeur, David J. Kriegman, Alan L. Yuille

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...

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection (1997)

Peter N. Belhumeur, Joao P. Hespanha, P. Hespanha, David J. Kriegman

We develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression.

Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection (1997)

Peter N. Belhumeur, P. Hespanha, David J. Kriegman

Abstract—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...

c ○ 1999 Kluwer Academic Publishers. Manufactured in The Netherlands. The Bas-Relief Ambiguity (1997)

Peter N. Belhumeur, David J. Kriegman, Alan L. Yuille

Abstract. When an unknown object with Lambertian reflectance is viewed orthographically, there is an implicit ambiguity in determining its 3-d structure: we show that the object’s visible surface f...

Real-time tracking of image regions with changes in geometry and illumination (1996)

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection (1996)

Historically, SSD or correlation-based visual tracking algorithms have been sensitive to changes in illumination and shading across the target region. This paper describes methods for implementing...

Peter N. Belhumeur, João P. Hespanha, Jo~ao P. Hespanha, David J. Kriegman

. We develop a face recognition algorithm which is insensitive to gross variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an...

Estimation of Motion Boundary Location and Optical Flow using Dynamic Programming (1996)

Estimation Of Motion Boundary Location And Optical Flow Using Dynamic Programming (1996)

We present a new method for the estimation of optical flow which uses a dynamic programming-based algorithm to simultaneously detect the presence of motion boundaries and to estimate optical flow....

Estimation of Motion Boundary Location and Optical Flow using Dynamic Programming (1996)

We present a new method for the estimation of optical flow which uses a dynamic programming based algorithm to simultaneously detect the presence of motion boundaries and to estimate optical flow....

Real-time tracking of image regions with changes in geometry and illumination (1996)

We present a new method for the estimation of optical flow which uses a dynamic programming-based algorithm to simultaneously detect the presence of motion boundaries and to estimate optical flow....

What is the Set of Images of an Object Under All Possible Lighting Conditions (1996)

Historically, SSD or correlation-based visual tracking algorithms have been sensitive to changes in illumination and shading across the target region. This paper describes methods for implementing...

Peter N. Belhumeur, David J. Kriegmant

The appearance of a particular object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for...

What is the set of images of an object under all possible lighting conditions (1996)

Peter N. Belhumeur, David J. Kriegman

The appearance of an object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for any pose...

Estimation of motion boundary location and optical flow using dynamic programming (1996)