Download:
|
by Jitendra Malik, Ruth Rosenholtz
http://HTTP.CS.Berkeley.EDU/projects/vision/papers/MalikRosenholtz.ps.gz
Add To MetaCart
Abstract:
Abstract. Shape from texture is best analyzed in two stages, analogous to stereopsis and structure from motion: (a) Computing the `texture distortion ' from the image, and (b) Interpreting the `texture distortion ' to infer the orientation and shape of the surface in the scene. We model the texture distortion for a given point and direction on the image plane as an affine transformation and derive the relationship between the parameters of this transformation and the shape parameters. We have developed a technique for estimating affine transforms between nearby image patches which is based on solving a system of linear constraints derived from a differential analysis. One need not explicitly identify texels or make restrictive assumptions about the nature of the texture such as isotropy. We use non-linear minimization of a least squares error criterion to recover the surface orientation (slant and tilt) and shape (principal curvatures and directions) based on the estimated affine transforms in a number of different directions. A simple linear algorithm based on singular value decomposition of the linear parts of the affine transforms provides the initial guess for the minimization procedure. Experimental results on both planar and curved surfaces under perspective projection demonstrate good estimates for both orientation and shape. A sensitivity analysis yields predictions for both computer vision algorithms and human perception of shape from texture. 1.
Citations
|
684
|
Robust regression and outlier detection
– ROUSSEEUW, LEROY
- 1987
|
|
188
|
The Perception of the Visual World
– Gibson
- 1950
|
|
110
|
Elementary Differential Geometry
– O’Neill
- 1966
|
|
88
|
Dynamic shape
– Koenderink, Doorn
- 1986
|
|
56
|
Shape from texture: estimation, isotropy and moments
– Blake, Marinos
- 1989
|
|
54
|
Riemannian Geometry
– Carmo, M
- 1993
|
|
48
|
Texture gradient as a depth cue
– Bajcsy, Lieberman
- 1976
|
|
46
|
Introduction to Shannon Sampling and Interpolation Theory
– Marks
- 1991
|
|
40
|
Shape from Texture Using Local Spectral Moments
– Super, Bovik
- 1995
|
|
39
|
Shape from texture for smooth curved surfaces
– Garding
- 1992
|
|
34
|
Shape from texture: general principle
– Kanatani, Chou
- 1989
|
|
33
|
Surface orientation from projective foreshortening of isotopic texture autocorrelation
– Brown, Shvaytser
- 1990
|
|
30
|
Shape from Texture from a Multi-Scale Perspective
– Lindeberg, G˚arding
- 1993
|
|
29
|
Shape from texture: Integrating texture-element extraction and surface estimation
– Blostein, Ahuja
- 1989
|
|
29
|
Three gradients and the perception of flat and curved surfaces
– Cutting, Millard
- 1984
|
|
28
|
Shape from Texture
– Aloimonos
- 1988
|
|
23
|
Shape from texture and contour by weak isotropy
– Garding
- 1993
|
|
22
|
Shape from periodic texture using spectrogram
– Krumm, Shafer
- 1992
|
|
21
|
A di erential method for computing local shape-from-texture for planar and curved surfaces
– Malik, Rosenholtz
- 1993
|
|
20
|
The information content of texture gradients
– Stevens
- 1981
|
|
19
|
Determining Three-Dimensional Shape from Orientation and Spatial Frequency Disparities
– Jones, Malik
- 1992
|
|
17
|
Differential techniques for optical flow
– Girosi, Verri, et al.
- 1990
|
|
16
|
Shape from texture: ideal observers and human psychophysics, Vision Res
– Blake, Bulthoff, et al.
- 1993
|
|
15
|
Shape from texture: The homogeneity hypothesis
– Marinos, Blake
- 1990
|
|
14
|
E cient recovery of shape from texture
– Davis, Janos, et al.
- 1983
|
|
14
|
ªRecovering Surface Curvature and Orientation from Texture Distortion, a Least Squares Algorithm and Sensitive Analysis,º
– Malik, Rosenholtz
- 1994
|
|
10
|
Shape from regular patterns
– Ikeuchi
- 1984
|
