Lambertian reflectance and linear subspaces

By Ronen Basri, David W. Jacobs. Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, 2001

1,944 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition, Ecology

View Paper: https://www.semanticscholar.org/paper/66e6a411a7342203ebbc22fbe9a3740b744d7cbc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

In Ecology

Citations in the corpus

Toward Guaranteed Illumination Models for Non-convex Objects (2013, background): “Finally, motivated by [1], we also consider the subspace S spanned by 9 principal components of C1.”
Total Moving Face Reconstruction (2014, methodology): “We assume Lambertian reflectance and use the 1st order spherical harmonics (SH) approximation to Lambertian reflectance [6] to model the relationship between surface normals and image intensities.”
Scattering Representations for Recognition (2013, background): “Since global illumination and rigid affine transformations define both low-dimensional manifolds [BJ03], θ can be thought as a low-dimensional random vector.”
Illumination Invariant Face Recognition Using Near-Infrared Images (2007, methodology): “Ramamoorthi [22] and Basri and Jacobs [23] independently used the spherical harmonic representation to explain the low dimensionality of face images under different illumination.”
Acquiring linear subspaces for face recognition under variable lighting (2005, methodology): “In the past few years, many appearance-based methods have been proposed to handle this problem, and new theoretical insights, as well as good recognition results, have been reported [1], [2], [3], [5], [7], [9].”
Eigenfeature Regularization and Extraction in Face Recognition (2008, background): “The agree-able properties of the linear subspace analysis and its promising performance achieved in the face recognition encourage researchers to extend it to higher order statistics [10], [11], nonlinear methods [12], [13], [14], Gabor features [15], [16], and locality preserving projections [17],…”
Gabor Feature Based Sparse Representation for Face Recognition with Gabor Occlusion Dictionary (2010, neutral): “harmonic plane or illumination cone [17], [18].”
SfSNet: Learning Shape, Reflectance and Illuminance of Faces 'in the Wild' (2017, background): “The image formation process under lambertian reflectance, following [3] is represented in equation (1), where frender(.”
Robust Online Multi-Task Learning with Correlative and Personalized Structures (2017, background): “For example, face images of an individual under different lighting conditions span a low-dimensional subspace from an ambient high-dimensional space [40].”
Live face detection based on the analysis of Fourier spectra (2004, background): “…in access control, automated crowd surveillance, law enforcement, information safety, multimedia communication, human-machine interface, etc. Compared to other biometric authentication technologies, face recognition has an obvious advantage that it does not need much cooperation from users.”
Robust Photometric Stereo via Low-Rank Matrix Completion and Recovery (2010, background): “Basri and Jacobs [5] and Georghiades et al .”
Face Recognition Under Varying Illumination Using Gradientfaces (2009, methodology): “The spherical harmonic model [12], [ 13 ] is applied to represent the low-dimensional subspace of different illumination face images.”
Spectral Curvature Clustering (SCC) (2009, background): “It has been proved that the set of all images of a Lambertian object under a variety of lighting conditions form a convex polyhedral cone in the image space, and this cone can be accurately approximated by a low-dimensional linear subspace (of dimension at most 9) (Ho et al. 2003; Basri and Jacobs 2”
Plenoxels: Radiance Fields without Neural Networks (2021, background): “Spherical harmonics are a standard basis for functions over the sphere, and have been used previously to represent view dependence [4, 36, 47, 58, 59].”
Fast L1-Minimization Algorithms For Robust Face Recognition (2010, neutral): “In this paper, we are not concerned about these pursuit-type greedy algorithms, but instead refer the reader to [33], [4], [34] for a more detailed treatment of the greedy approach. under different illuminations lies closely to a low-dimensional subspace, called face subspace [37], [38].”
Discriminative K-SVD for dictionary learning in face recognition (2010, background): “It has been observed that images of human face under varying illumination conditions and expressions lie on a special low-dimensional space [3][2].”
Example-based photometric stereo: shape reconstruction with general, varying BRDFs (2005, methodology): “An interesting topic for future work is to determine the requisite number of images under general situations, perhaps using the frequency-domain analysis of Basri and Jacobs [4] and Ramamoorthi and Hanranan [25].”