Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons

@article{Leung2004RepresentingAR,
  title={Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons},
  author={Thomas K. Leung and Jitendra Malik},
  journal={International Journal of Computer Vision},
  year={2004},
  volume={43},
  pages={29-44}
}
We study the recognition of surfaces made from different materials such as concrete, rug, marble, or leather on the basis of their textural appearance. Such natural textures arise from spatial variation of two surface attributes: (1) reflectance and (2) surface normal. In this paper, we provide a unified model to address both these aspects of natural texture. The main idea is to construct a vocabulary of prototype tiny surface patches with associated local geometric and photometric properties… 
Shape, Illumination and Material Properties from Surface Appearance
The appearance of a surface depends on its material, as well as the illumination and the surface shape. The aim of this work is to develop a computational framework in which all these aspects are
Hybrid textons: modeling surfaces with reflectance and geometry
TLDR
A texture representation that integrates appearance-based information from the sampled BTF with concise geometric information inferred from the sample BTF is presented, which has key advantages in a wide range of tasks, including texture prediction, recognition, and synthesis.
Classifying Images of Materials: Achieving Viewpoint and Illumination Independence
TLDR
This paper presents a novel method of classifying a single image without requiring any a priori knowledge about the viewing or illumination conditions under which it was photographed, and argues that using rotationally invariant filters while clustering in such a low dimensional space improves classification performance.
Material Classification under Natural Illumination Using Reflectance Maps
TLDR
This work proposes a system that only requires the 3D shape of objects and a regular, commercial camera to capture their appearance in a single image, to perform material classification under unknown illumination, and relies on a Gaussian Process Latent Variable Model with a discriminative prior for material classification of reflectance maps.
3D Texture Recognition Using Bidirectional Feature Histograms
TLDR
A 3D texture recognition method is designed which employs the BFH as the surface model, and classifies surfaces based on a single novel texture image of unknown imaging parameters, and a computational method for quantitatively evaluating the relative significance of texture images within the BTF is developed.
Fine-Grained Material Classification Using Micro-geometry and Reflectance
TLDR
This paper introduces a new, publicly available database for fine-grained material classification, consisting of over 2000 surfaces of fabrics, and shows that the fusion of normals and albedo information outperforms standard methods which rely only on the use of texture information.
Bidirectional Texture Function Modeling: A State of the Art Survey
  • J. Filip, M. Haindl
  • Computer Science, Medicine
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2009
TLDR
This paper categorize, critically survey, and psychophysically compare the first BTF measurement, compression, modeling, and rendering methods, which were published in this newly arising and important computer vision and graphics area.
Conversions between three methods for representing 3D surface textures under arbitrary illumination directions
TLDR
A single mathematical framework is introduced and used to express three commonly used surface texture relighting representations: surface gradients (Gradient), Polynomial Texture Maps (PTM) and eigen base images (Eigen), and from this a set of conversion methods are proposed.
Using Basic Image Features for Texture Classification
TLDR
This paper investigates the performance of an approach which represents textures as histograms over a visual vocabulary which is defined geometrically, based on the Basic Image Features of Griffin and Lillholm, rather than by clustering.
Advanced textural representation of materials appearance
TLDR
Options as to which type of material representation is appropriate for required application, what are its limits and possible modelling options, and what the biggest challenges in realistic modelling of materials are are are discussed.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 47 REFERENCES
Recognizing surfaces using three-dimensional textons
  • T. Leung, Jitendra Malik
  • Computer Science
    Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
TLDR
A unified model to address both the reflectance and surface normal aspects of natural texture and to construct a vocabulary of prototype tiny surface patches with associated local geometric and photometric properties is provided.
On perpendicular texture or: Why do we see more flowers in the distance?
  • T. Leung, Jitendra Malik
  • Mathematics, Computer Science
    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
TLDR
The geometry of the problem is studied, modeling the locations of the elements of the texture as being a realization of a spatial point process, and Relations between slant and tilt of the surface, density and height of elements and occlusions are derived.
Correlation model for 3D texture
  • K. Dana, S. Nayar
  • Mathematics, Computer Science
    Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
TLDR
This work presents a correlation model for a particular class of 3D textures that characterizes the spatial relationship among neighboring pixels in an image of3D texture and the change of this spatial relationship with viewing direction.
Histogram model for 3D textures
  • K. Dana, S. Nayar
  • Computer Science
    Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)
  • 1998
TLDR
This work presents a concise analytical model for the bidirectional histogram of Lambertian, isotropic, randomly rough surfaces, which are common in real-world scenes and demonstrates the usefulness of the model by employing it in a novel 3D texture synthesis procedure.
Textons, contours and regions: cue integration in image segmentation
TLDR
An operational definition of textons, the putative elementary units of texture perception, and an algorithm for partitioning the image into disjoint regions of coherent brightness and texture, where boundaries of regions are defined by peaks in contour orientation energy and differences in texton densities across the contour.
On Photometric Issues in 3D Visual Recognition from a Single 2D Image
  • A. Shashua
  • Mathematics, Computer Science
    International Journal of Computer Vision
  • 2004
TLDR
The paper is motivated by empirical evidence inspired by Mooney images of faces that suggest a relatively high level of visual processing is involved in compensating for photometric sources of variability, and furthermore, that certain limitations on the admissible representations of image information may exist.
Reflectance and texture of real-world surfaces
TLDR
The visual appearance of real-world surfaces and the dependence of appearance on imaging conditions is investigated and a BRDF (bidirectional reflectance distribution function) database with reflectance measurements for over 60 different samples, each observed with over 200 different combinations of viewing and source directions is presented.
Illumination cones for recognition under variable lighting: faces
TLDR
This method is both an implementation and extension (an extension in that it models cast shadows) of the illumination cone representation proposed in Belhumeur and Kriegman (1996), and the results exceed those of popular existing methods.
Visual learning and recognition of 3-d objects from appearance
TLDR
A near real-time recognition system with 20 complex objects in the database has been developed and a compact representation of object appearance is proposed that is parametrized by pose and illumination.
3D Textured Surface Modeling
TLDR
The work on investigating and modeling surface detail using the framework of the BRDF (bidirectional reflectance distribution function) and the BTF (biddirectional texture function) is discussed.
...
1
2
3
4
5
...