Results 1  10
of
65
From Few to many: Illumination cone models for face recognition under variable lighting and pose
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 2001
"... We present a generative appearancebased 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 possible illumination conditions, is a convex cone in the space of images. Using a smal ..."
Abstract

Cited by 479 (12 self)
 Add to MetaCart
We present a generative appearancebased 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 possible illumination conditions, is a convex cone in the space of images. Using a small number of training images of each face taken with different lighting directions, the shape and albedo of the face can be reconstructed. In turn, this reconstruction serves as a generative model that can be used to render—or synthesize—images of the face under novel poses and illumination conditions. The pose space is then sampled, and for each pose the corresponding illumination cone is approximated by a lowdimensional linear subspace whose basis vectors are estimated using the generative model. Our recognition algorithm assigns to a test image the identity of the closest approximated illumination cone (based on Euclidean distance within the image space). We test our face recognition method on 4050 images from the Yale Face Database B; these images contain 405 viewing conditions (9 poses ¢ 45 illumination conditions) for 10 individuals. The method performs almost without error, except on the most extreme lighting directions, and significantly outperforms popular recognition methods that do not use a generative model.
Lambertian Reflectance and Linear Subspaces
, 2000
"... We prove that the set of all reflectance functions (the mapping from surface normals to intensities) produced by Lambertian objects under distant, isotropic lighting lies close to a 9D linear subspace. This implies that, in general, the set of images of a convex Lambertian object obtained under a wi ..."
Abstract

Cited by 365 (20 self)
 Add to MetaCart
We prove that the set of all reflectance functions (the mapping from surface normals to intensities) produced by Lambertian objects under distant, isotropic lighting lies close to a 9D linear subspace. This implies that, in general, the set of images of a convex Lambertian object obtained under a wide variety of lighting conditions can be approximated accurately by a lowdimensional linear subspace, explaining prior empirical results. We also provide a simple analytic characterization of this linear space. We obtain these results by representing lighting using spherical harmonics and describing the effects of Lambertian materials as the analog of a convolution. These results allow us to construct algorithms for object recognition based on linear methods as well as algorithms that use convex optimization to enforce nonnegative lighting functions. Finally, we show a simple way to enforce nonnegative lighting when the images of an object lie near a 4D linear space. Research conducted w...
What is the Set of Images of an Object Under All Possible Lighting Conditions
 IEEE CVPR
, 1996
"... 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 any pose or lighting conditions, then in theory the objects can always be distinguished or recogni ..."
Abstract

Cited by 345 (27 self)
 Add to MetaCart
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 any pose or lighting conditions, then in theory the objects can always be distinguished or recognized. The question arises: What is the set of images of an object under all lighting conditions and pose? In this paper, ive consider only the set of images of an object under variable allumination (including multiple, extended light sources and attached shadows). We prove that the set of npixel images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a convex polyhedral cone in IR " and that the dimension of this illumination cone equals the number of distinct surface normals. Furthermore, we show that the cone for a particular object can be constructed from three properly chosen images. Finally, we prove that the set of npixel images of an object of any shape and with an arbitrary reflectance function, seen under all possible illumination conditions, still forms a convex cone in Rn. Th.ese results immediately suggest certain approaches to object recognition. Throughout this paper, we ofler results demonstrating the empirical validity of the illumination cone representation. 1
Deriving Intrinsic Images from Image Sequences
, 2001
"... Intrinsic images are a useful midlevel description of scenes proposed by Barrow and Tenebaum [1]. An image is decomposed into two images: a reflectance image and an illumination image. Finding such a decomposition remains a difficult problem in computer vision. Here we focus on a slightly easier pro ..."
Abstract

Cited by 198 (5 self)
 Add to MetaCart
Intrinsic images are a useful midlevel description of scenes proposed by Barrow and Tenebaum [1]. An image is decomposed into two images: a reflectance image and an illumination image. Finding such a decomposition remains a difficult problem in computer vision. Here we focus on a slightly easier problem: given a sequence of T images where the reflectance is constant and the illumination changes, can we recover T illumination images and a single reflectance image? We show that this problem is still illposed and suggest approaching it as a maximumlikelihood estimation problem. Following recent work on the statistics of natural images, we use a prior that assumes that illumination images will give rise to sparse filter outputs. We show that this leads to a simple, novel algorithm for recovering reflectance images. We illustrate the algorithm's performance on real and synthetic image sequences.
Helmholtz Stereopsis: Exploiting Reciprocity for Surface Reconstruction
 International Journal of Computer Vision
, 2002
"... 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 (e.g., stereo vision, structure from motion, photometric stereo), Helmholtz stereopsis makes no assumptions ab ..."
Abstract

Cited by 100 (13 self)
 Add to MetaCart
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 (e.g., stereo vision, structure from motion, photometric stereo), Helmholtz stereopsis makes no assumptions about the nature of the bidirectional reflectance distribution functions (BRDFs) of objects. This new method of multinocular stereopsis exploits Helmholtz reciprocity by choosing pairs of light source and camera positions that guarantee that the ratio of the emitted radiance to the incident irradiance is the same for corresponding points in the two images. The method provides direct estimates of both depth and field of surface normals, and consequently weds the advantages of both conventional and photometric stereopsis. Results from our implementations lend empirical support to our technique. 1
From Few to Many: Generative Models for Recognition Under Variable Pose and Illumination
, 2000
"... Abstract Image variability due to changes in pose and illumination can seriously impair object recognition. This paper presents appearancebased methods which, unlike previous appearancebased approaches, require only a small set of training images to generate a rich representation that models this ..."
Abstract

Cited by 98 (8 self)
 Add to MetaCart
Abstract Image variability due to changes in pose and illumination can seriously impair object recognition. This paper presents appearancebased methods which, unlike previous appearancebased approaches, require only a small set of training images to generate a rich representation that models this variability. Specifically, from as few as three images of an object in fixed pose seen under slightly varying but unknown lighting, a surface and an albedo map are reconstructed. These are then used to generate synthetic images with large variations in pose and illumination and thus build a representation useful for object recognition. Our methods have been tested within the domain of face recognition on a subset of the Yale Face Database B containing 4050 images of 10 faces seen under variable pose and illumination. This database was specifically gathered for testing these generative methods. Their performance is shown to exceed that of popular existing methods. 1 Introduction An object can appear strikingly different due to changes in pose and illumination (see Figure 1). To handle this image variability, object recognition systems usually use one of the following approaches: (a) control viewing conditions, (b) employ a representation that is invariant to the viewing conditions, or (c) directly model this variability. For example, there is a long tradition of performing edge detection at an early stage since the presence of an edge at an image location is thought to be largely independent of lighting. It has been observed, however, that methods for face recognition based on finding local image features and using their geometric relation are generally ineffective [4].
Photometric Stereo with General, Unknown Lighting
 In IEEE Conference on Computer Vision and Pattern Recognition
, 2001
"... Work on photometric stereo has shown how to recover the shape and reflectance properties of an object using multiple images taken with a fixed viewpoint and variable lighting conditions. This work has primarily relied on the presence of a single point source of light in each image. In this paper we ..."
Abstract

Cited by 96 (8 self)
 Add to MetaCart
Work on photometric stereo has shown how to recover the shape and reflectance properties of an object using multiple images taken with a fixed viewpoint and variable lighting conditions. This work has primarily relied on the presence of a single point source of light in each image. In this paper we show how to perform photometric stereo assuming that all lights in a scene are isotropic and distant from the object but otherwise unconstrained. Lighting in each image may be an unknown and arbitrary combination of diffuse, point and extended sources. Our work is based on recent results showing that for Lambertian objects, general lighting conditions can be represented using low order spherical harmonics. Using this representation we can recover shape by performing a simple optimization in a lowdimensional space. We also analyze the shape ambiguities that arise in such a representation. 1.
Determining generative models of objects under varying illumination: Shape and albedo from multiple images using svd and integrability
 International Journal of Computer Vision
, 1999
"... We describe a method of learning generative models of objects from a set of images of the object under different, and unknown, illumination. Such a model allows us to approximate the objects’ appearance under a range of lighting conditions. This work is closely related to photometric stereo with unk ..."
Abstract

Cited by 71 (3 self)
 Add to MetaCart
We describe a method of learning generative models of objects from a set of images of the object under different, and unknown, illumination. Such a model allows us to approximate the objects’ appearance under a range of lighting conditions. This work is closely related to photometric stereo with unknown light sources and, in particular, to the use of Singular Value Decomposition (SVD) to estimate shape and albedo from multiple images up to a linear transformation [15]. Firstly we analyze and extend the SVD approach to this problem. We demonstrate that it applies to objects for which the dominant imaging effects are Lambertian reflectance with a distant light source and a background ambient term. To determine that this is a reasonable approximation we calculate the eigenvectors of the SVD on a set of real objects, under varying lighting conditions, and demonstrate that the first few eigenvectors account for most of the data in agreement with our predictions. We then analyze the linear ambiguities in the SVD approach and demonstrate that previous methods proposed to resolve them [15] are only valid under certain conditions. We discuss alternative possibilities and, in particular, demonstrate that knowledge of the object class is sufficient to resolve this problem. Secondly, we describe the use of surface consistency for putting constraints on the possible solutions. We prove that this constraint reduces the ambiguities to a subspace called the generalized bas relief ambiguity (GBR) which is inherent in the Lambertian reflectance function (and which can be shown to exist even if attached and cast shadows are present [3]). We demonstrate the use of surface consistency to solve for the shape and albedo up to a GBR and describe, and implement, a variety of additional assumptions to resolve the GBR. Thirdly, we demonstrate an iterative algorithm that can detect and remove some attached shadows from the objects thereby increasing the accuracy of the reconstructed shape and albedo. 1
Damped Newton algorithms for matrix factorization with missing data
 in CVPR05
, 2005
"... The problem of lowrank matrix factorization in the presence of missing data has seen significant attention in recent computer vision research. The approach that dominates the literature is EMlike alternation of closedform solutions for the two factors of the matrix. An obvious alternative is nonl ..."
Abstract

Cited by 68 (0 self)
 Add to MetaCart
The problem of lowrank matrix factorization in the presence of missing data has seen significant attention in recent computer vision research. The approach that dominates the literature is EMlike alternation of closedform solutions for the two factors of the matrix. An obvious alternative is nonlinear optimization of both factors simultaneously, a strategy which has seen little published research. This paper provides a comprehensive comparison of the two strategies by evaluating previously published factorization algorithms as well as some second order methods not previously presented for this problem. We conclude that, although alternation approaches can be very quick, their propensity to glacial convergence in narrow valleys of the cost function means that averagecase performance is worse than secondorder strategies. Further, we demonstrate the importance of two main observations: one, that schemes based on closedform solutions alone are not suitable and that nonlinear optimization strategies are faster, more accurate and provide more flexible frameworks for continued progress; and two, that basic objective functions are not adequate and that regularization priors must be incorporated, a process that is easier with nonlinear methods. 1.