Color Subspaces as Photometric Invariants

Authors:
Todd Zickler;Satya P. Mallick;David J. Kriegman;Peter N. Belhumeur
Affiliations:
Harvard University, Cambridge, USA 02138;University of California, San Diego, USA;University of California, San Diego, USA;Columbia University, New York, USA 10027
Venue:
International Journal of Computer Vision
Year:
2008

Citing 41
Cited 9

Modeling Light Reflection for Computer Color Vision

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Theory of Photometric Stereo for a Class of Diffuse Non-Lambertian Surfaces

IEEE Transactions on Pattern Analysis and Machine Intelligence
Constraining Object Features Using a Polarization Reflectance Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimation of Illuminant Direction, Albedo, and Shape from Shading

IEEE Transactions on Pattern Analysis and Machine Intelligence
Reflectance based object recognition

International Journal of Computer Vision
Color in Perspective

IEEE Transactions on Pattern Analysis and Machine Intelligence
Separation of Reflection Components Using Color and Polarization

International Journal of Computer Vision
Stereo and Specular Reflection

International Journal of Computer Vision
Color and Illuminant Voting

IEEE Transactions on Pattern Analysis and Machine Intelligence
Reflectance and Shape from Images Using a Collinear Light Source

International Journal of Computer Vision
A practical model for subsurface light transport

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
A practical model for subsurface light transport

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Color by Correlation: A Simple, Unifying Framework for Color Constancy

IEEE Transactions on Pattern Analysis and Machine Intelligence
Removing Shadows from Images

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Helmholtz Stereopsis: Exploiting Reciprocity for Surface Reconstruction

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Diffuse-Specular Separation and Depth Recovery from Image Sequences

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Photometric Stereo for Non-Lambertian Surfaces Using Color Information

CAIP '93 Proceedings of the 5th International Conference on Computer Analysis of Images and Patterns
Markov Random Fields with Efficient Approximations

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Multibaseline Stereo in the Presence of Specular Reflections

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Quantitative Color Optical Flow

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 4 - Volume 4
Image-based skin color and texture analysis/synthesis by extracting hemoglobin and melanin information in the skin

ACM SIGGRAPH 2003 Papers
The use of color in computational vision

The use of color in computational vision
Depth Discontinuities by Pixel-to-Pixel Stereo

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Face Recognition Based on Fitting a 3D Morphable Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Dealing with Textureless Regions and Specular Highlights-A Progressive Space Carving Scheme Using a Novel Photo-consistency Measure

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Shape and Motion under Varying Illumination: Unifying Structure from Motion, Photometric Stereo, and Multi-view Stereo

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Separating Reflection Components of Textured Surfaces using a Single Image

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
A Class of Photometric Invariants: Separating Material from Shape and Illumination

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Binocular Helmholtz Stereopsis

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance

International Journal of Computer Vision
BRDF Invariant Stereo Using Light Transport Constancy

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Passive Photometric Stereo from Motion

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Adaptive Support-Weight Approach for Correspondence Search

IEEE Transactions on Pattern Analysis and Machine Intelligence
A New Formulation for Shape from Shading for Non-Lambertian Surfaces

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Separation of Highlight Reflections on Textured Surfaces

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Shape and materials by example: a photometric stereo approach

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Surface reconstruction via helmholtz reciprocity with a single image pair

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Specularity removal in images and videos: a PDE approach

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Correspondence search in the presence of specular highlights using specular-free two-band images

ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
The 4-source photometric stereo technique for three-dimensional surfaces in the presence of highlights and shadows

IEEE Transactions on Pattern Analysis and Machine Intelligence
A comparison of computational color constancy Algorithms. II. Experiments with image data

IEEE Transactions on Image Processing

Generic Scene Recovery Using Multiple Images

SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision
Joint Estimation of Shape and Reflectance using Multiple Images with Known Illumination Conditions

International Journal of Computer Vision
Estimating Facial Reflectance Properties Using Shape-from-Shading

International Journal of Computer Vision
A Solution of the Dichromatic Model for Multispectral Photometric Invariance

International Journal of Computer Vision
A color neuromorphic approach for motion estimation

WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Towards full 3D Helmholtz stereovision algorithms

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
Perception based representations for computational colour

CCIW'11 Proceedings of the Third international conference on Computational color imaging
Specular-free residual minimization for photometric stereo with unknown light sources

PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part I
Shape from fluorescence

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 mitigate these effects is to explore functions of an image that are invariant to these photometric events. In this paper we describe a class of such invariants that result from exploiting color information in images of dichromatic surfaces. These invariants are derived from illuminant-dependent `subspaces' of RGB color space, and they enable the application of Lambertian-based vision techniques to a broad class of specular, non-Lambertian scenes. Using implementations of recent algorithms taken from the literature, we demonstrate the practical utility of these invariants for a wide variety of applications, including stereo, shape from shading, photometric stereo, material-based segmentation, and motion estimation.